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/military_defense_expense.md

@@ -0,0 +1,64 @@
+---
+entity_slug: military_defense_expense
+evaluator: null
+evaluated_at: '2026-02-23T05:52:25.440602'
+overall_score: 4.2
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly specifies what constitutes military defense expense
+    (armed forces, naval forces, war expenditures) and identifies the key asymmetry
+    that the mother country bears costs while colonies receive benefits. It avoids
+    circularity and captures a distinct economic concept with measurable components.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This concept is directly grounded in Smith's analysis in Book IV, Chapter
+    7, where he extensively discusses the costs of colonial defense and argues that
+    Britain bears disproportionate military expenses relative to the benefits received
+    from colonial trade monopolies.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"Regulation" is appropriate since this involves government policy decisions
+    about resource allocation and colonial administration. However, it could also
+    fit in a "Public Finance" or "Imperial Economics" domain, as it fundamentally
+    concerns fiscal burdens and imperial cost-benefit analysis.'
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: This entity has moderate VSM relevance, primarily mapping to S1 (operational
+    costs of maintaining empire) and S4 (environmental threats requiring defensive
+    response). However, it's more of a cost category than a systemic function, making
+    the VSM mapping somewhat forced.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides crucial explanatory power for Smith's critique of
+    mercantilism by quantifying the hidden costs of empire that offset supposed benefits
+    from colonial monopolies. It illuminates the structural mechanism by which imperial
+    systems create fiscal burdens that undermine their purported advantages.
+---
+
+# Evaluation: Military Defense Expense
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly specifies what constitutes military defense expense (armed forces, naval forces, war expenditures) and identifies the key asymmetry that the mother country bears costs while colonies receive benefits. It avoids circularity and captures a distinct economic concept with measurable components.
+
+## source_grounding — 5.0 / 5.0
+
+This concept is directly grounded in Smith's analysis in Book IV, Chapter 7, where he extensively discusses the costs of colonial defense and argues that Britain bears disproportionate military expenses relative to the benefits received from colonial trade monopolies.
+
+## domain_placement — 4.0 / 5.0
+
+"Regulation" is appropriate since this involves government policy decisions about resource allocation and colonial administration. However, it could also fit in a "Public Finance" or "Imperial Economics" domain, as it fundamentally concerns fiscal burdens and imperial cost-benefit analysis.
+
+## vsm_relevance — 3.0 / 5.0
+
+This entity has moderate VSM relevance, primarily mapping to S1 (operational costs of maintaining empire) and S4 (environmental threats requiring defensive response). However, it's more of a cost category than a systemic function, making the VSM mapping somewhat forced.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides crucial explanatory power for Smith's critique of mercantilism by quantifying the hidden costs of empire that offset supposed benefits from colonial monopolies. It illuminates the structural mechanism by which imperial systems create fiscal burdens that undermine their purported advantages.