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_geography_determinism.md

@@ -0,0 +1,61 @@
+---
+entity_slug: economic_geography_determinism
+evaluator: null
+evaluated_at: '2026-02-23T05:10:29.821204'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly distinguishes between geographical features determining
+    economic patterns versus merely influencing them, and specifies the mechanisms
+    (market extent, division of labour). The concept is well-bounded and avoids circularity.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This directly reflects Smith's explicit argument in Book I, Chapter 3
+    about how water-carriage determines the initial location of industry and the sequence
+    of economic development from coastal to inland areas. The deterministic framing
+    accurately captures Smith's strong causal claims.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"General Theory" is the correct domain placement as this represents
+    a fundamental theoretical principle about how geography shapes economic development
+    patterns, rather than a specific mechanism or policy application.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This maps well to S4 (intelligence/environmental adaptation) as it concerns
+    how economic systems must adapt to and work within geographical constraints and
+    opportunities. It represents a key environmental factor that shapes system viability.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: This provides genuine explanatory power by identifying geography as a
+    structural determinant of economic possibilities, helping explain why certain
+    development patterns emerge and why market extent varies systematically across
+    locations.
+---
+
+# Evaluation: Economic Geography Determinism
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly distinguishes between geographical features determining economic patterns versus merely influencing them, and specifies the mechanisms (market extent, division of labour). The concept is well-bounded and avoids circularity.
+
+## source_grounding — 5.0 / 5.0
+
+This directly reflects Smith's explicit argument in Book I, Chapter 3 about how water-carriage determines the initial location of industry and the sequence of economic development from coastal to inland areas. The deterministic framing accurately captures Smith's strong causal claims.
+
+## domain_placement — 5.0 / 5.0
+
+"General Theory" is the correct domain placement as this represents a fundamental theoretical principle about how geography shapes economic development patterns, rather than a specific mechanism or policy application.
+
+## vsm_relevance — 4.0 / 5.0
+
+This maps well to S4 (intelligence/environmental adaptation) as it concerns how economic systems must adapt to and work within geographical constraints and opportunities. It represents a key environmental factor that shapes system viability.
+
+## explanatory_value — 4.0 / 5.0
+
+This provides genuine explanatory power by identifying geography as a structural determinant of economic possibilities, helping explain why certain development patterns emerge and why market extent varies systematically across locations.