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_administrative_efficiency.md

@@ -0,0 +1,62 @@
+---
+entity_slug: colonial_administrative_efficiency
+evaluator: null
+evaluated_at: '2026-02-23T04:44:22.416964'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly distinguishes colonial administrative efficiency
+    as effectiveness relative to cost in managing public affairs, with specific components
+    (services, order, policy implementation). It avoids circularity and captures a
+    distinct concept of governmental performance measurement.
+- name: source_grounding
+  value: 4.0
+  max_value: 5.0
+  rationale: Smith does discuss colonial administration costs and effectiveness in
+    Book IV, Chapter 7, particularly when arguing about colonial contributions to
+    imperial expenses. The entity accurately reflects his observations about the relatively
+    modest costs of effective local colonial government.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Regulation" is the correct domain placement since this concerns governmental
+    administrative functions and oversight mechanisms. The concept directly relates
+    to how regulatory and administrative systems operate within colonial contexts.'
+- name: vsm_relevance
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity maps clearly to S3 (internal regulation/audit) as it concerns
+    the effectiveness of administrative oversight and control functions. It also has
+    relevance to S1 (operations) regarding the delivery of basic governmental services.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: The entity illuminates an important structural mechanism in Smith's colonial
+    analysis - how administrative effectiveness enables greater fiscal contributions.
+    It explains the relationship between governmental efficiency and imperial fiscal
+    policy rather than merely describing surface phenomena.
+---
+
+# Evaluation: Colonial Administrative Efficiency
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly distinguishes colonial administrative efficiency as effectiveness relative to cost in managing public affairs, with specific components (services, order, policy implementation). It avoids circularity and captures a distinct concept of governmental performance measurement.
+
+## source_grounding — 4.0 / 5.0
+
+Smith does discuss colonial administration costs and effectiveness in Book IV, Chapter 7, particularly when arguing about colonial contributions to imperial expenses. The entity accurately reflects his observations about the relatively modest costs of effective local colonial government.
+
+## domain_placement — 5.0 / 5.0
+
+"Regulation" is the correct domain placement since this concerns governmental administrative functions and oversight mechanisms. The concept directly relates to how regulatory and administrative systems operate within colonial contexts.
+
+## vsm_relevance — 5.0 / 5.0
+
+This entity maps clearly to S3 (internal regulation/audit) as it concerns the effectiveness of administrative oversight and control functions. It also has relevance to S1 (operations) regarding the delivery of basic governmental services.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity illuminates an important structural mechanism in Smith's colonial analysis - how administrative effectiveness enables greater fiscal contributions. It explains the relationship between governmental efficiency and imperial fiscal policy rather than merely describing surface phenomena.