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/colony_economic_policy_effectiveness.md

@@ -0,0 +1,63 @@
+---
+entity_slug: colony_economic_policy_effectiveness
+evaluator: null
+evaluated_at: '2026-02-23T04:52:51.929409'
+overall_score: 4.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a distinct concept about policy outcomes versus
+    intentions, but "effectiveness" remains somewhat vague without clearer metrics
+    or criteria. The reference to "mismatch between metropolitan interests and colonial
+    economic realities" adds helpful specificity.
+- name: source_grounding
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity appears well-grounded in Smith's actual analysis of colonial
+    policies in Book V, Chapter 3, where he systematically critiques various colonial
+    economic arrangements. Smith does indeed argue that many colonial policies have
+    been counterproductive due to misaligned interests.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Regulation" is the correct domain placement, as this entity directly
+    concerns the effectiveness of regulatory policies imposed on colonies. The concept
+    sits squarely within questions of economic governance and policy implementation.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it evaluates
+    regulatory performance, and also connects to S4 (intelligence/environmental adaptation)
+    regarding the mismatch between policy design and local conditions. The VSM lens
+    illuminates the systemic nature of policy effectiveness.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: "The entity provides genuine explanatory power by identifying a structural\
+    \ mechanism\u2014the disconnect between metropolitan policy-makers and colonial\
+    \ realities\u2014that explains why colonial policies often fail. This goes beyond\
+    \ surface description to reveal underlying causal relationships."
+---
+
+# Evaluation: Colony Economic Policy Effectiveness
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a distinct concept about policy outcomes versus intentions, but "effectiveness" remains somewhat vague without clearer metrics or criteria. The reference to "mismatch between metropolitan interests and colonial economic realities" adds helpful specificity.
+
+## source_grounding — 4.0 / 5.0
+
+This entity appears well-grounded in Smith's actual analysis of colonial policies in Book V, Chapter 3, where he systematically critiques various colonial economic arrangements. Smith does indeed argue that many colonial policies have been counterproductive due to misaligned interests.
+
+## domain_placement — 5.0 / 5.0
+
+"Regulation" is the correct domain placement, as this entity directly concerns the effectiveness of regulatory policies imposed on colonies. The concept sits squarely within questions of economic governance and policy implementation.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it evaluates regulatory performance, and also connects to S4 (intelligence/environmental adaptation) regarding the mismatch between policy design and local conditions. The VSM lens illuminates the systemic nature of policy effectiveness.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity provides genuine explanatory power by identifying a structural mechanism—the disconnect between metropolitan policy-makers and colonial realities—that explains why colonial policies often fail. This goes beyond surface description to reveal underlying causal relationships.