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_selection.md

@@ -0,0 +1,66 @@
+---
+entity_slug: economic_system_selection
+evaluator: null
+evaluated_at: '2026-02-23T05:20:45.530965'
+overall_score: 3.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a coherent concept about choosing economic arrangements,
+    but it's somewhat broad and could apply to many decision-making processes. The
+    phrase "based on their circumstances, objectives, and understanding" is quite
+    general and doesn't specify what makes this selection process distinct from other
+    policy choices.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss different systems being appropriate for different
+    nations and ages, the entity appears to extrapolate a formal "selection process"
+    that isn't explicitly theorized in the source text. Smith's observations about
+    system appropriateness don't necessarily constitute a theory of how nations actively
+    choose between systems.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate since this concept would span across
+    different economic domains rather than belonging to a specific area like trade
+    or taxation. The broad nature of system selection as a meta-level concept supports
+    this placement.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S5 (identity/policy) as it concerns fundamental
+    decisions about a nation's economic identity and governing principles. It could
+    also relate to S4 (intelligence/adaptation) insofar as system selection requires
+    environmental assessment and strategic adaptation.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity names a phenomenon but doesn't illuminate the mechanisms by
+    which such selection occurs or the structural relations that govern it. It remains
+    at a high level of abstraction without providing insight into how or why nations
+    actually make these choices.
+---
+
+# Evaluation: Economic System Selection
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a coherent concept about choosing economic arrangements, but it's somewhat broad and could apply to many decision-making processes. The phrase "based on their circumstances, objectives, and understanding" is quite general and doesn't specify what makes this selection process distinct from other policy choices.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss different systems being appropriate for different nations and ages, the entity appears to extrapolate a formal "selection process" that isn't explicitly theorized in the source text. Smith's observations about system appropriateness don't necessarily constitute a theory of how nations actively choose between systems.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate since this concept would span across different economic domains rather than belonging to a specific area like trade or taxation. The broad nature of system selection as a meta-level concept supports this placement.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S5 (identity/policy) as it concerns fundamental decisions about a nation's economic identity and governing principles. It could also relate to S4 (intelligence/adaptation) insofar as system selection requires environmental assessment and strategic adaptation.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity names a phenomenon but doesn't illuminate the mechanisms by which such selection occurs or the structural relations that govern it. It remains at a high level of abstraction without providing insight into how or why nations actually make these choices.