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/agricultural_productivity.md

@@ -0,0 +1,64 @@
+---
+entity_slug: agricultural_productivity
+evaluator: null
+evaluated_at: '2026-02-23T00:31:03.242713'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly distinguishes agricultural productivity as efficiency
+    of output per unit of land/labor, with specific measurement criteria. It avoids
+    circularity and captures a distinct economic concept, though it could be slightly
+    more precise about what constitutes "efficiency."
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is well-grounded in Book I, Chapter 11, where Smith extensively
+    discusses agricultural improvements, their effects on land rents, and the relationship
+    between agricultural productivity and food costs. The connection to land rents
+    and economic development directly reflects Smith's analysis.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Production" is the correct domain assignment, as agricultural productivity
+    fundamentally concerns the efficiency of productive processes in agriculture.
+    This aligns perfectly with Smith''s treatment of it as a production-side factor
+    affecting rents and costs.'
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: Agricultural productivity maps primarily to S1 (primary operations) as
+    a core productive activity, with some relevance to S4 (adaptation through technological
+    improvements). However, it's somewhat abstract as a measure of efficiency rather
+    than a concrete operational or regulatory mechanism.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides strong explanatory power by illuminating the causal
+    mechanism between agricultural improvements, land rents, food costs, and broader
+    economic development. It captures a key structural relationship in Smith's economic
+    theory rather than just naming a surface phenomenon.
+---
+
+# Evaluation: Agricultural Productivity
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly distinguishes agricultural productivity as efficiency of output per unit of land/labor, with specific measurement criteria. It avoids circularity and captures a distinct economic concept, though it could be slightly more precise about what constitutes "efficiency."
+
+## source_grounding — 5.0 / 5.0
+
+This entity is well-grounded in Book I, Chapter 11, where Smith extensively discusses agricultural improvements, their effects on land rents, and the relationship between agricultural productivity and food costs. The connection to land rents and economic development directly reflects Smith's analysis.
+
+## domain_placement — 5.0 / 5.0
+
+"Production" is the correct domain assignment, as agricultural productivity fundamentally concerns the efficiency of productive processes in agriculture. This aligns perfectly with Smith's treatment of it as a production-side factor affecting rents and costs.
+
+## vsm_relevance — 3.0 / 5.0
+
+Agricultural productivity maps primarily to S1 (primary operations) as a core productive activity, with some relevance to S4 (adaptation through technological improvements). However, it's somewhat abstract as a measure of efficiency rather than a concrete operational or regulatory mechanism.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides strong explanatory power by illuminating the causal mechanism between agricultural improvements, land rents, food costs, and broader economic development. It captures a key structural relationship in Smith's economic theory rather than just naming a surface phenomenon.