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/expense_of_defence.md

@@ -0,0 +1,64 @@
+---
+entity_slug: expense_of_defence
+evaluator: null
+evaluated_at: '2026-02-23T05:25:20.397017'
+overall_score: 4.0
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition is clear and specific, identifying both the scope (military
+    forces for external protection) and temporal aspects (peacetime preparation and
+    wartime employment). It avoids circularity and captures a distinct fiscal concept
+    rather than a vague umbrella term.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is directly grounded in Smith's text as the first of three
+    sovereign duties explicitly outlined in Book V, Chapter 1. Smith dedicates substantial
+    analysis to military expenditure across different stages of societal development,
+    making this a core concept rather than an interpretive addition.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: The "Regulation" domain is appropriate since this concerns the sovereign's
+    regulatory duty to provide defense as a public good. While it has fiscal dimensions,
+    it fundamentally represents a regulatory function that markets cannot adequately
+    provide.
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: This entity spans multiple VSM systems - it involves S1 (operational
+    military forces), S3 (internal resource allocation), and S4 (environmental threat
+    assessment). While relevant to VSM thinking, it doesn't map cleanly to a single
+    system, making it somewhat diffuse for VSM analysis.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity illuminates a fundamental structural mechanism in Smith's
+    theory - how societies must allocate resources to defense and how this varies
+    with economic development stages. It explains the relationship between economic
+    organization and military capability rather than merely naming a surface phenomenon.
+---
+
+# Evaluation: Expense Of Defence
+
+## definition_precision — 4.0 / 5.0
+
+The definition is clear and specific, identifying both the scope (military forces for external protection) and temporal aspects (peacetime preparation and wartime employment). It avoids circularity and captures a distinct fiscal concept rather than a vague umbrella term.
+
+## source_grounding — 5.0 / 5.0
+
+This entity is directly grounded in Smith's text as the first of three sovereign duties explicitly outlined in Book V, Chapter 1. Smith dedicates substantial analysis to military expenditure across different stages of societal development, making this a core concept rather than an interpretive addition.
+
+## domain_placement — 4.0 / 5.0
+
+The "Regulation" domain is appropriate since this concerns the sovereign's regulatory duty to provide defense as a public good. While it has fiscal dimensions, it fundamentally represents a regulatory function that markets cannot adequately provide.
+
+## vsm_relevance — 3.0 / 5.0
+
+This entity spans multiple VSM systems - it involves S1 (operational military forces), S3 (internal resource allocation), and S4 (environmental threat assessment). While relevant to VSM thinking, it doesn't map cleanly to a single system, making it somewhat diffuse for VSM analysis.
+
+## explanatory_value — 4.0 / 5.0
+
+This entity illuminates a fundamental structural mechanism in Smith's theory - how societies must allocate resources to defense and how this varies with economic development stages. It explains the relationship between economic organization and military capability rather than merely naming a surface phenomenon.