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_policy_effectiveness.md

@@ -0,0 +1,64 @@
+---
+entity_slug: colonial_economic_policy_effectiveness
+evaluator: null
+evaluated_at: '2026-02-23T04:46:52.881287'
+overall_score: 4.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a meaningful concept about policy effectiveness
+    but remains somewhat vague with phrases like "intended economic outcomes" and
+    "more open policies typically prove more effective." It could be more precise
+    about what constitutes effectiveness and how it's measured.
+- name: source_grounding
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity is well-grounded in Smith's actual analysis in Book IV, Chapter
+    7, where he extensively critiques monopolistic colonial policies and argues for
+    more liberal approaches. The characterization of Smith's position on policy effectiveness
+    versus monopoly approaches accurately reflects the source text.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Regulation" domain is perfectly appropriate for this entity, as
+    it directly concerns the effectiveness of different regulatory approaches to colonial
+    management. This is fundamentally about regulatory policy choices and their outcomes.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it concerns
+    evaluating and optimizing regulatory approaches, and potentially S4 (intelligence/adaptation)
+    as it involves learning which policies work better in different environments.
+    It has clear VSM relevance for organizational learning and regulatory effectiveness.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity provides genuine explanatory power by illuminating the structural
+    relationship between policy approach (monopolistic vs. open) and outcomes, helping
+    explain why certain colonial policies systematically failed while others succeeded.
+    It reveals an important mechanism in Smith's economic thinking about institutional
+    design.
+---
+
+# Evaluation: Colonial Economic Policy Effectiveness
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a meaningful concept about policy effectiveness but remains somewhat vague with phrases like "intended economic outcomes" and "more open policies typically prove more effective." It could be more precise about what constitutes effectiveness and how it's measured.
+
+## source_grounding — 4.0 / 5.0
+
+This entity is well-grounded in Smith's actual analysis in Book IV, Chapter 7, where he extensively critiques monopolistic colonial policies and argues for more liberal approaches. The characterization of Smith's position on policy effectiveness versus monopoly approaches accurately reflects the source text.
+
+## domain_placement — 5.0 / 5.0
+
+The "Regulation" domain is perfectly appropriate for this entity, as it directly concerns the effectiveness of different regulatory approaches to colonial management. This is fundamentally about regulatory policy choices and their outcomes.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it concerns evaluating and optimizing regulatory approaches, and potentially S4 (intelligence/adaptation) as it involves learning which policies work better in different environments. It has clear VSM relevance for organizational learning and regulatory effectiveness.
+
+## explanatory_value — 4.0 / 5.0
+
+This entity provides genuine explanatory power by illuminating the structural relationship between policy approach (monopolistic vs. open) and outcomes, helping explain why certain colonial policies systematically failed while others succeeded. It reveals an important mechanism in Smith's economic thinking about institutional design.