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/colonial_wine_duty_drawback.md

@@ -0,0 +1,58 @@
+---
+entity_slug: colonial_wine_duty_drawback
+evaluator: null
+evaluated_at: '2026-02-23T04:52:16.348245'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: "The definition is quite precise, specifying exact duty amounts (\xA3\
+    3, 10s.), the timing (after 1763), and clear exceptions (French wines). It captures\
+    \ a distinct policy mechanism rather than a vague concept."
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity appears to be directly grounded in Smith's specific discussion
+    of drawback policies in Book IV, Chapter 4, with concrete details that suggest
+    direct textual reference rather than interpretation.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Regulation" is the correct domain assignment as this describes a specific
+    government policy mechanism for administering trade duties and drawbacks.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This maps well to S3 (internal regulation) as it represents a specific
+    operational control mechanism for managing trade flows, and potentially S2 (coordination)
+    for managing colonial-metropolitan economic relationships.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity illuminates how political considerations (anti-French sentiment)
+    could override economic efficiency in trade policy design, demonstrating the intersection
+    of mercantile strategy and national prejudice in regulatory mechanisms.
+---
+
+# Evaluation: Colonial Wine Duty Drawback
+
+## definition_precision — 4.0 / 5.0
+
+The definition is quite precise, specifying exact duty amounts (£3, 10s.), the timing (after 1763), and clear exceptions (French wines). It captures a distinct policy mechanism rather than a vague concept.
+
+## source_grounding — 5.0 / 5.0
+
+This entity appears to be directly grounded in Smith's specific discussion of drawback policies in Book IV, Chapter 4, with concrete details that suggest direct textual reference rather than interpretation.
+
+## domain_placement — 5.0 / 5.0
+
+"Regulation" is the correct domain assignment as this describes a specific government policy mechanism for administering trade duties and drawbacks.
+
+## vsm_relevance — 4.0 / 5.0
+
+This maps well to S3 (internal regulation) as it represents a specific operational control mechanism for managing trade flows, and potentially S2 (coordination) for managing colonial-metropolitan economic relationships.
+
+## explanatory_value — 4.0 / 5.0
+
+This entity illuminates how political considerations (anti-French sentiment) could override economic efficiency in trade policy design, demonstrating the intersection of mercantile strategy and national prejudice in regulatory mechanisms.