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/buss_fishery.md

@@ -0,0 +1,62 @@
+---
+entity_slug: buss_fishery
+evaluator: null
+evaluated_at: '2026-02-23T04:39:22.323215'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition is precise and specific, clearly distinguishing buss-fishery
+    by vessel size (20-80 tons), deck configuration, and operational scale. It avoids
+    circularity and captures a distinct fishing method rather than a vague category.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is directly grounded in Smith's text from Book IV, Chapter
+    5, where he explicitly discusses the buss-fishery bounty system and its effects.
+    The context accurately reflects Smith's critical analysis of these government
+    subsidies.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Production" domain assignment is correct, as buss-fishery represents
+    a specific method of productive activity in the fishing industry. This fits naturally
+    within Smith's broader analysis of different production systems and their efficiency.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S1 (primary operations) as a specific production
+    method, and to S4 (intelligence/adaptation) through Smith's analysis of how bounty
+    systems distort natural market adaptation. The regulatory critique also touches
+    on S3 concerns about internal resource allocation.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: The entity illuminates Smith's broader argument about how government
+    interventions can distort natural economic efficiency by favoring capital-intensive
+    operations over locally-adapted methods. It demonstrates the mechanism by which
+    bounties create artificial competitive advantages that may reduce overall productivity.
+---
+
+# Evaluation: Buss Fishery
+
+## definition_precision — 4.0 / 5.0
+
+The definition is precise and specific, clearly distinguishing buss-fishery by vessel size (20-80 tons), deck configuration, and operational scale. It avoids circularity and captures a distinct fishing method rather than a vague category.
+
+## source_grounding — 5.0 / 5.0
+
+This entity is directly grounded in Smith's text from Book IV, Chapter 5, where he explicitly discusses the buss-fishery bounty system and its effects. The context accurately reflects Smith's critical analysis of these government subsidies.
+
+## domain_placement — 5.0 / 5.0
+
+The "Production" domain assignment is correct, as buss-fishery represents a specific method of productive activity in the fishing industry. This fits naturally within Smith's broader analysis of different production systems and their efficiency.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S1 (primary operations) as a specific production method, and to S4 (intelligence/adaptation) through Smith's analysis of how bounty systems distort natural market adaptation. The regulatory critique also touches on S3 concerns about internal resource allocation.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity illuminates Smith's broader argument about how government interventions can distort natural economic efficiency by favoring capital-intensive operations over locally-adapted methods. It demonstrates the mechanism by which bounties create artificial competitive advantages that may reduce overall productivity.