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/economic_system_governance.md

@@ -0,0 +1,63 @@
+---
+entity_slug: economic_system_governance
+evaluator: null
+evaluated_at: '2026-02-23T05:16:30.410269'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is overly broad and umbrella-like, essentially describing
+    all forms of economic governance without identifying a specific, distinct concept.
+    It reads more like a general description of institutional frameworks than a precise
+    conceptual definition.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss political economy as "the science of the statesman
+    or legislator," this entity extrapolates far beyond what Smith actually articulates,
+    introducing modern governance terminology and concepts not present in the source
+    text. The connection to Smith's actual discussion is tenuous at best.
+- name: domain_placement
+  value: 3.0
+  max_value: 5.0
+  rationale: The "Regulation" domain is reasonable given the governance focus, though
+    the entity is so broad it could arguably fit in multiple domains. The domain assignment
+    is not incorrect but reflects the entity's lack of conceptual specificity.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to multiple VSM systems, particularly S3 (internal
+    regulation), S4 (intelligence/adaptation), and S5 (identity/policy), making it
+    highly relevant to VSM analysis. The governance focus aligns naturally with VSM's
+    emphasis on regulatory and control mechanisms.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity provides little explanatory power beyond naming a general
+    category of phenomena that most readers would already understand. It doesn't illuminate
+    specific mechanisms or structural relations that would enhance understanding of
+    Smith's economic theory.
+---
+
+# Evaluation: Economic System Governance
+
+## definition_precision — 2.0 / 5.0
+
+The definition is overly broad and umbrella-like, essentially describing all forms of economic governance without identifying a specific, distinct concept. It reads more like a general description of institutional frameworks than a precise conceptual definition.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss political economy as "the science of the statesman or legislator," this entity extrapolates far beyond what Smith actually articulates, introducing modern governance terminology and concepts not present in the source text. The connection to Smith's actual discussion is tenuous at best.
+
+## domain_placement — 3.0 / 5.0
+
+The "Regulation" domain is reasonable given the governance focus, though the entity is so broad it could arguably fit in multiple domains. The domain assignment is not incorrect but reflects the entity's lack of conceptual specificity.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to multiple VSM systems, particularly S3 (internal regulation), S4 (intelligence/adaptation), and S5 (identity/policy), making it highly relevant to VSM analysis. The governance focus aligns naturally with VSM's emphasis on regulatory and control mechanisms.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity provides little explanatory power beyond naming a general category of phenomena that most readers would already understand. It doesn't illuminate specific mechanisms or structural relations that would enhance understanding of Smith's economic theory.