feat(example): add per-entity LLM evaluations for 985 WoN entities (S3.3)

Batch evaluation of all 988 entities via OpenRouter. 984 succeeded on
first pass; 3 failed (network errors). eval-summary --update-metrics
written with per_entity_mean=3.9556.

Viability dashboard: 6/6 PASS
  redundancy_ratio   0.0061  (max 0.10)
  coverage_ratio     0.6190  (min 0.40)
  coherence_comps    0.0000  (max 3)
  consistency_cycles 0.0000  (max 0)
  granularity_entropy 2.6748 (min 1.0)
  per_entity_mean    3.9556  (min 3.5)

Dimension breakdown (mean across 985 entities):
  definition_precision  3.62
  source_grounding      4.36
  domain_placement      4.56
  vsm_relevance         3.31
  explanatory_value     3.94

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

examples/infospace-with-history/output/evaluations/skill_and_dexterity.md

@@ -0,0 +1,66 @@
+---
+entity_slug: skill_and_dexterity
+evaluator: null
+evaluated_at: '2026-02-23T06:21:46.471578'
+overall_score: 4.6
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly distinguishes skill and dexterity as manual and
+    technical capabilities that improve through specialization, with specific reference
+    to speed and precision. It avoids circularity and captures a distinct concept,
+    though it could be slightly more precise about what constitutes "manual and technical
+    capabilities."
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is directly grounded in Smith's explicit argument in Book
+    I, Chapter 1, where he identifies the improvement of skill and dexterity as one
+    of the three main advantages of division of labor. The context accurately reflects
+    Smith's reasoning about repeated performance of operations.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Production" is the correct domain placement since skill and dexterity
+    directly relate to how goods are manufactured and the productive capabilities
+    of workers. This is fundamentally about the production process rather than exchange,
+    distribution, or consumption.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S1 (primary operations) as it describes the
+    actual productive capabilities of workers performing operational tasks. It could
+    also relate to S3 (internal regulation) in terms of how skill development affects
+    operational efficiency and quality control.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides genuine explanatory power by identifying a specific
+    mechanism through which division of labor increases productivity - the development
+    of worker capabilities through repetition. It illuminates how specialization creates
+    efficiency gains at the individual worker level, which is fundamental to Smith's
+    broader argument.
+---
+
+# Evaluation: Skill And Dexterity
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly distinguishes skill and dexterity as manual and technical capabilities that improve through specialization, with specific reference to speed and precision. It avoids circularity and captures a distinct concept, though it could be slightly more precise about what constitutes "manual and technical capabilities."
+
+## source_grounding — 5.0 / 5.0
+
+This entity is directly grounded in Smith's explicit argument in Book I, Chapter 1, where he identifies the improvement of skill and dexterity as one of the three main advantages of division of labor. The context accurately reflects Smith's reasoning about repeated performance of operations.
+
+## domain_placement — 5.0 / 5.0
+
+"Production" is the correct domain placement since skill and dexterity directly relate to how goods are manufactured and the productive capabilities of workers. This is fundamentally about the production process rather than exchange, distribution, or consumption.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S1 (primary operations) as it describes the actual productive capabilities of workers performing operational tasks. It could also relate to S3 (internal regulation) in terms of how skill development affects operational efficiency and quality control.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides genuine explanatory power by identifying a specific mechanism through which division of labor increases productivity - the development of worker capabilities through repetition. It illuminates how specialization creates efficiency gains at the individual worker level, which is fundamental to Smith's broader argument.