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_economic_system.md

@@ -0,0 +1,64 @@
+---
+entity_slug: colonial_economic_system
+evaluator: null
+evaluated_at: '2026-02-23T04:50:40.956601'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly delineates the colonial system's key components
+    (exclusive trade, administrative control, military protection) and its fundamental
+    asymmetric relationship structure. It avoids circularity and captures the essential
+    economic dependency mechanism Smith critiques.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity directly reflects Smith's extensive analysis in Book IV,
+    Chapter 8, where he systematically examines colonial costs versus benefits and
+    critiques the mercantile colonial framework. The definition accurately captures
+    his core arguments about colonies as economic dependencies and cost burdens.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Regulation" is the correct domain placement as Smith treats the colonial
+    system as a regulatory framework that artificially constrains trade flows and
+    market relationships. This fits perfectly within his broader critique of mercantile
+    regulations that distort natural economic processes.'
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: The colonial system spans multiple VSM functions - S1 (economic operations),
+    S3 (administrative control), and S4 (strategic positioning) - making it somewhat
+    diffuse from a VSM perspective. While it has clear regulatory and operational
+    aspects, it doesn't map cleanly to a single VSM system.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides substantial explanatory power by illuminating the
+    structural mechanisms of colonial economic extraction and control that Smith identifies
+    as fundamentally inefficient. It reveals how regulatory frameworks can create
+    systematic economic distortions rather than merely naming a historical phenomenon.
+---
+
+# Evaluation: Colonial Economic System
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly delineates the colonial system's key components (exclusive trade, administrative control, military protection) and its fundamental asymmetric relationship structure. It avoids circularity and captures the essential economic dependency mechanism Smith critiques.
+
+## source_grounding — 5.0 / 5.0
+
+This entity directly reflects Smith's extensive analysis in Book IV, Chapter 8, where he systematically examines colonial costs versus benefits and critiques the mercantile colonial framework. The definition accurately captures his core arguments about colonies as economic dependencies and cost burdens.
+
+## domain_placement — 5.0 / 5.0
+
+"Regulation" is the correct domain placement as Smith treats the colonial system as a regulatory framework that artificially constrains trade flows and market relationships. This fits perfectly within his broader critique of mercantile regulations that distort natural economic processes.
+
+## vsm_relevance — 3.0 / 5.0
+
+The colonial system spans multiple VSM functions - S1 (economic operations), S3 (administrative control), and S4 (strategic positioning) - making it somewhat diffuse from a VSM perspective. While it has clear regulatory and operational aspects, it doesn't map cleanly to a single VSM system.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides substantial explanatory power by illuminating the structural mechanisms of colonial economic extraction and control that Smith identifies as fundamentally inefficient. It reveals how regulatory frameworks can create systematic economic distortions rather than merely naming a historical phenomenon.