run_id: a25fbeed2ef7
workflow_id: generic-source-evaluations
status: completed
dry_run: false
inputs:
- name: entity
  artifact_id: entity/entity-title-bucket-shop.md
  kind: entity
  title: 'Entity Title: Bucket Shop'
  path: artifacts/entities/entity-title-bucket-shop.md
  slug: entity-title-bucket-shop
  content: "# Entity Title: Bucket Shop  \n## Definition  \nA type of brokerage that\
    \ allows customers to place bets on the price movements of stocks without actually\
    \ owning them, often engaging in manipulative practices to profit at the expense\
    \ of the bettors.  \n## Category  \nmarket  \n## Context  \nThe practice of manipulating\
    \ stock prices to wipe out long positions of customers.  \n## Source Evidence\
    \  \n\"whenever a bucket shop found itself loaded with too many bulls on a certain\
    \ stock it was a common practice to get some broker to wash down the price of\
    \ that particular stock far enough to wipe out all the customers that were long\
    \ of it.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-sugar.md
  kind: entity
  title: 'Entity Title: Sugar'
  path: artifacts/entities/entity-title-sugar.md
  slug: entity-title-sugar
  content: "# Entity Title: Sugar  \n## Definition  \nA specific stock that traders\
    \ engage with, which is central to the narratives involving trading strategies\
    \ and market manipulation.  \n## Category  \ninstrument  \n## Context  \nSugar\
    \ is referenced in the context of a market manipulation scheme executed by bucket\
    \ shops.  \n## Source Evidence  \n\"Henry Williams and I together were short six\
    \ thousand shares of Sugar.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-cosmopolitan.md
  kind: entity
  title: 'Entity Title: Cosmopolitan'
  path: artifacts/entities/entity-title-cosmopolitan.md
  slug: entity-title-cosmopolitan
  content: "# Entity Title: Cosmopolitan  \n## Definition  \nA particular bucket shop\
    \ involved in market manipulation strategies to profit off the misfortunes of\
    \ its clients.  \n## Category  \ninstitution  \n## Context  \nThe Cosmopolitan\
    \ employed market manipulation tactics that contributed to the losses of certain\
    \ traders.  \n## Source Evidence  \n\"That was what the Cosmopolitan did to get\
    \ me and Henry Williams and the other Sugar shorts.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-market-drive.md
  kind: entity
  title: 'Entity Title: Market Drive'
  path: artifacts/entities/entity-title-market-drive.md
  slug: entity-title-market-drive
  content: "# Entity Title: Market Drive  \n## Definition  \nA tactic employed to\
    \ artificially inflate or deflate stock prices in a way that leads to trader losses\
    \ and profits for others.  \n## Category  \nstrategy  \n## Context  \nRefers to\
    \ the strategy used by operators to manipulate stock prices causing losses for\
    \ long holders.  \n## Source Evidence  \n\"whenever there was an unexplained sharp\
    \ drop which was followed by instant recovery, the newspapers in those days used\
    \ to call it a bucket-shop drive.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-dollar-manipulation.md
  kind: entity
  title: 'Entity Title: Dollar Manipulation'
  path: artifacts/entities/entity-title-dollar-manipulation.md
  slug: entity-title-dollar-manipulation
  content: "# Entity Title: Dollar Manipulation  \n## Definition  \nThe practice of\
    \ manipulating stock prices to extract profits from the market, often at the expense\
    \ of average investors.  \n## Category  \nerror  \n## Context  \nIt underscores\
    \ the dangers of participating in manipulative market practices without adequate\
    \ knowledge.  \n## Source Evidence  \n\"Their brokers in New York ran up the price\
    \ to 108. Of course it fell right back, but Henry and a lot of others were wiped\
    \ out.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-new-york-stock-exchange.md
  kind: entity
  title: 'Entity Title: New York Stock Exchange'
  path: artifacts/entities/entity-title-new-york-stock-exchange.md
  slug: entity-title-new-york-stock-exchange
  content: "# Entity Title: New York Stock Exchange  \n## Definition  \nA premier\
    \ stock exchange in the United States where stocks are bought and sold, often\
    \ used as a backdrop for trading strategies and manipulations.  \n## Category\
    \  \nmarket  \n## Context  \nThe trading activities of the Cosmopolitan and other\
    \ manipulators influence prices on this exchange.  \n## Source Evidence  \n\"\
    They made thousands of dollars... to thimblerig the market on the New York Stock\
    \ Exchange and wipe us out.\"  \n\n---\n"
- name: entity
  artifact_id: entity/entity-title-western-union.md
  kind: entity
  title: 'Entity Title: Western Union'
  path: artifacts/entities/entity-title-western-union.md
  slug: entity-title-western-union
  content: "# Entity Title: Western Union  \n## Definition  \nA specific stock favored\
    \ for trading due to its liquidity and ease of price manipulation.  \n## Category\
    \  \ninstrument  \n## Context  \nReferencing a stock used strategically to execute\
    \ manipulative trades benefiting the instigator.  \n## Source Evidence  \n\"One\
    \ of his favorite stocks was Western Union, because it was so easy to move a semiactive\
    \ stock like that a few points up or down.\"\n"
stages:
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-bucket-shop.md
  output_artifact_id: generated/evaluation-entity-title-bucket-shop.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144756-F2bJ3ZaZ42YKYakYEJie
    usage:
      prompt_tokens: 474
      completion_tokens: 164
      total_tokens: 638
      cost: 0.0001695
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.0001695
        upstream_inference_prompt_cost: 7.11e-05
        upstream_inference_completions_cost: 9.84e-05
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 2.926
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-sugar.md
  output_artifact_id: generated/evaluation-entity-title-sugar.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144760-wIcanekwnL9b2LgOQ42x
    usage:
      prompt_tokens: 423
      completion_tokens: 166
      total_tokens: 589
      cost: 0.00016305
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.00016305
        upstream_inference_prompt_cost: 6.345e-05
        upstream_inference_completions_cost: 9.96e-05
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 3.274
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-cosmopolitan.md
  output_artifact_id: generated/evaluation-entity-title-cosmopolitan.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144764-wYbhNJCoMZ5wVKnssriA
    usage:
      prompt_tokens: 431
      completion_tokens: 209
      total_tokens: 640
      cost: 0.00019005
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.00019005
        upstream_inference_prompt_cost: 6.465e-05
        upstream_inference_completions_cost: 0.0001254
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 4.312
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-market-drive.md
  output_artifact_id: generated/evaluation-entity-title-market-drive.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144769-4K7MOuMXn5mtFLbyvAG8
    usage:
      prompt_tokens: 447
      completion_tokens: 200
      total_tokens: 647
      cost: 0.00018705
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.00018705
        upstream_inference_prompt_cost: 6.705e-05
        upstream_inference_completions_cost: 0.00012
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 5.621
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-dollar-manipulation.md
  output_artifact_id: generated/evaluation-entity-title-dollar-manipulation.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144775-ViGFYJom73LDw5YHCwu6
    usage:
      prompt_tokens: 446
      completion_tokens: 218
      total_tokens: 664
      cost: 0.0001977
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.0001977
        upstream_inference_prompt_cost: 6.69e-05
        upstream_inference_completions_cost: 0.0001308
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 4.039
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-new-york-stock-exchange.md
  output_artifact_id: generated/evaluation-entity-title-new-york-stock-exchange.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144780-vyDzUBQfmtnJvNOKHxdC
    usage:
      prompt_tokens: 450
      completion_tokens: 232
      total_tokens: 682
      cost: 0.0002067
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.0002067
        upstream_inference_prompt_cost: 6.75e-05
        upstream_inference_completions_cost: 0.0001392
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 4.628
- stage_id: evaluate-entity
  kind: assisted
  status: completed
  input_artifact_id: entity/entity-title-western-union.md
  output_artifact_id: generated/evaluation-entity-title-western-union.md
  provider: openrouter
  metadata:
    model: openai/gpt-4o-mini
    request_id: gen-1779144786-Yzt9LTYwAqYqcwflBeWW
    usage:
      prompt_tokens: 438
      completion_tokens: 146
      total_tokens: 584
      cost: 0.0001533
      is_byok: false
      prompt_tokens_details:
        cached_tokens: 0
        cache_write_tokens: 0
        audio_tokens: 0
        video_tokens: 0
      cost_details:
        upstream_inference_cost: 0.0001533
        upstream_inference_prompt_cost: 6.57e-05
        upstream_inference_completions_cost: 8.76e-05
      completion_tokens_details:
        reasoning_tokens: 0
        image_tokens: 0
        audio_tokens: 0
    retry_count: 0
    duration_seconds: 3.078
outputs:
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-bucket-shop.md
  path: output/evaluations/entity-title-bucket-shop.md
  kind: generated
  title: 'Entity Title: Bucket Shop Evaluation'
  input_artifact_id: entity/entity-title-bucket-shop.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-sugar.md
  path: output/evaluations/entity-title-sugar.md
  kind: generated
  title: 'Entity Title: Sugar Evaluation'
  input_artifact_id: entity/entity-title-sugar.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-cosmopolitan.md
  path: output/evaluations/entity-title-cosmopolitan.md
  kind: generated
  title: 'Entity Title: Cosmopolitan Evaluation'
  input_artifact_id: entity/entity-title-cosmopolitan.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-market-drive.md
  path: output/evaluations/entity-title-market-drive.md
  kind: generated
  title: 'Entity Title: Market Drive Evaluation'
  input_artifact_id: entity/entity-title-market-drive.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-dollar-manipulation.md
  path: output/evaluations/entity-title-dollar-manipulation.md
  kind: generated
  title: 'Entity Title: Dollar Manipulation Evaluation'
  input_artifact_id: entity/entity-title-dollar-manipulation.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-new-york-stock-exchange.md
  path: output/evaluations/entity-title-new-york-stock-exchange.md
  kind: generated
  title: 'Entity Title: New York Stock Exchange Evaluation'
  input_artifact_id: entity/entity-title-new-york-stock-exchange.md
  written: true
- stage_id: evaluate-entity
  artifact_id: generated/evaluation-entity-title-western-union.md
  path: output/evaluations/entity-title-western-union.md
  kind: generated
  title: 'Entity Title: Western Union Evaluation'
  input_artifact_id: entity/entity-title-western-union.md
  written: true
assisted_requests:
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-bucket-shop.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-bucket-shop.md\n\
    Entity title: Entity Title: Bucket Shop\n\n## Entity\n\n# Entity Title: Bucket\
    \ Shop  \n## Definition  \nA type of brokerage that allows customers to place\
    \ bets on the price movements of stocks without actually owning them, often engaging\
    \ in manipulative practices to profit at the expense of the bettors.  \n## Category\
    \  \nmarket  \n## Context  \nThe practice of manipulating stock prices to wipe\
    \ out long positions of customers.  \n## Source Evidence  \n\"whenever a bucket\
    \ shop found itself loaded with too many bulls on a certain stock it was a common\
    \ practice to get some broker to wash down the price of that particular stock\
    \ far enough to wipe out all the customers that were long of it.\"  \n\n---\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-sugar.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-sugar.md\n\
    Entity title: Entity Title: Sugar\n\n## Entity\n\n# Entity Title: Sugar  \n##\
    \ Definition  \nA specific stock that traders engage with, which is central to\
    \ the narratives involving trading strategies and market manipulation.  \n## Category\
    \  \ninstrument  \n## Context  \nSugar is referenced in the context of a market\
    \ manipulation scheme executed by bucket shops.  \n## Source Evidence  \n\"Henry\
    \ Williams and I together were short six thousand shares of Sugar.\"  \n\n---\n\
    \n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-cosmopolitan.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-cosmopolitan.md\n\
    Entity title: Entity Title: Cosmopolitan\n\n## Entity\n\n# Entity Title: Cosmopolitan\
    \  \n## Definition  \nA particular bucket shop involved in market manipulation\
    \ strategies to profit off the misfortunes of its clients.  \n## Category  \n\
    institution  \n## Context  \nThe Cosmopolitan employed market manipulation tactics\
    \ that contributed to the losses of certain traders.  \n## Source Evidence  \n\
    \"That was what the Cosmopolitan did to get me and Henry Williams and the other\
    \ Sugar shorts.\"  \n\n---\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-market-drive.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-market-drive.md\n\
    Entity title: Entity Title: Market Drive\n\n## Entity\n\n# Entity Title: Market\
    \ Drive  \n## Definition  \nA tactic employed to artificially inflate or deflate\
    \ stock prices in a way that leads to trader losses and profits for others.  \n\
    ## Category  \nstrategy  \n## Context  \nRefers to the strategy used by operators\
    \ to manipulate stock prices causing losses for long holders.  \n## Source Evidence\
    \  \n\"whenever there was an unexplained sharp drop which was followed by instant\
    \ recovery, the newspapers in those days used to call it a bucket-shop drive.\"\
    \  \n\n---\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-dollar-manipulation.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-dollar-manipulation.md\n\
    Entity title: Entity Title: Dollar Manipulation\n\n## Entity\n\n# Entity Title:\
    \ Dollar Manipulation  \n## Definition  \nThe practice of manipulating stock prices\
    \ to extract profits from the market, often at the expense of average investors.\
    \  \n## Category  \nerror  \n## Context  \nIt underscores the dangers of participating\
    \ in manipulative market practices without adequate knowledge.  \n## Source Evidence\
    \  \n\"Their brokers in New York ran up the price to 108. Of course it fell right\
    \ back, but Henry and a lot of others were wiped out.\"  \n\n---\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-new-york-stock-exchange.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-new-york-stock-exchange.md\n\
    Entity title: Entity Title: New York Stock Exchange\n\n## Entity\n\n# Entity Title:\
    \ New York Stock Exchange  \n## Definition  \nA premier stock exchange in the\
    \ United States where stocks are bought and sold, often used as a backdrop for\
    \ trading strategies and manipulations.  \n## Category  \nmarket  \n## Context\
    \  \nThe trading activities of the Cosmopolitan and other manipulators influence\
    \ prices on this exchange.  \n## Source Evidence  \n\"They made thousands of dollars...\
    \ to thimblerig the market on the New York Stock Exchange and wipe us out.\" \
    \ \n\n---\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
- stage_id: evaluate-entity
  workflow_id: generic-source-evaluations
  input_artifact_id: entity/entity-title-western-union.md
  prompt: "# Evaluate Trading-Literature Entity\n\nProfile: trading-literature\n\n\
    Evaluate the generated entity as Markdown with YAML frontmatter. Include\n`artifact_id`,\
    \ `evaluator`, `evaluated_at`, and a `scores` list. Score\neach criterion on a\
    \ 0 to 5 scale where 5 is best.\n\nRequired score names:\n\n- `groundedness` \u2014\
    \ does the entity stay anchored to the source chunk,\n  with no invented dates,\
    \ dollar figures, or quotes?\n- `lesson_clarity` \u2014 for `strategy`, `error`,\
    \ `psychological_pattern`,\n  and `evidence_bearing_claim` entities, is the operator-level\
    \ lesson\n  stated crisply enough to be reused in later chapters? For purely\n\
    \  factual entities (trader, market, institution, instrument), score\n  this on\
    \ the clarity of the definition.\n- `historical_context` \u2014 is the entity\
    \ placed correctly in the era and\n  venue of the source (e.g. early-1900s American\
    \ equities) without\n  importing modern terminology or instruments?\n- `overgeneralization_risk`\
    \ \u2014 is the entity scoped narrowly enough to\n  resist becoming a vague universal\
    \ claim? Higher score means lower\n  risk. Flag entities that quietly claim to\
    \ apply to all markets or\n  all operators when the source restricts the claim.\n\
    \nAdd a short `## Review Notes` section listing any specific lines from\nthe entity\
    \ body that drove a low score on any criterion.\n\nEntity artifact: entity/entity-title-western-union.md\n\
    Entity title: Entity Title: Western Union\n\n## Entity\n\n# Entity Title: Western\
    \ Union  \n## Definition  \nA specific stock favored for trading due to its liquidity\
    \ and ease of price manipulation.  \n## Category  \ninstrument  \n## Context \
    \ \nReferencing a stock used strategically to execute manipulative trades benefiting\
    \ the instigator.  \n## Source Evidence  \n\"One of his favorite stocks was Western\
    \ Union, because it was so easy to move a semiactive stock like that a few points\
    \ up or down.\"\n\n"
  provider_hint: openrouter
  metadata:
    output:
      path: output/evaluations/{{ input.slug }}.md
      kind: generated
      artifact_id: generated/evaluation-{{ input.slug }}.md
      title: '{{ input.title }} Evaluation'
recorded_at: '2026-05-18T22:53:11.449445+00:00'