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/colony_economic_system_learning.md

@@ -0,0 +1,67 @@
+---
+entity_slug: colony_economic_system_learning
+evaluator: null
+evaluated_at: '2026-02-23T04:54:46.751433'
+overall_score: 3.2
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a reasonably distinct concept about learning
+    processes in colonial economies, but uses somewhat vague terms like "effective
+    economic practices" and "gradual adaptation" without specifying what makes practices
+    effective or how adaptation occurs. The concept is identifiable but could be more
+    precisely delineated.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss colonial economic development in Book V, Chapter
+    3, the framing of this as a systematic "learning process" with trial-and-error
+    methodology appears to impose modern learning theory concepts onto Smith's text
+    rather than emerging directly from his analysis. Smith focuses more on structural
+    factors and policy effects than on learning mechanisms per se.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: The "Accumulation" domain is appropriate since colonial economic learning
+    would contribute to the development of productive capacity and wealth-building
+    processes over time. This fits well with Smith's broader themes about how economies
+    develop and improve their productive capabilities.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps clearly to S4 (intelligence/environmental adaptation)
+    as it describes how colonial economies gather information about their environment
+    and adapt their practices accordingly. The learning and observation processes
+    described are quintessential intelligence functions in the VSM framework.
+- name: explanatory_value
+  value: 3.0
+  max_value: 5.0
+  rationale: The entity identifies a potentially important mechanism for colonial
+    economic development, but remains at a fairly general level without illuminating
+    specific causal pathways or structural relationships. It names a phenomenon that
+    could be explanatorily valuable but doesn't develop the mechanism sufficiently
+    to provide deep insights.
+---
+
+# Evaluation: Colony Economic System Learning
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a reasonably distinct concept about learning processes in colonial economies, but uses somewhat vague terms like "effective economic practices" and "gradual adaptation" without specifying what makes practices effective or how adaptation occurs. The concept is identifiable but could be more precisely delineated.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss colonial economic development in Book V, Chapter 3, the framing of this as a systematic "learning process" with trial-and-error methodology appears to impose modern learning theory concepts onto Smith's text rather than emerging directly from his analysis. Smith focuses more on structural factors and policy effects than on learning mechanisms per se.
+
+## domain_placement — 4.0 / 5.0
+
+The "Accumulation" domain is appropriate since colonial economic learning would contribute to the development of productive capacity and wealth-building processes over time. This fits well with Smith's broader themes about how economies develop and improve their productive capabilities.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps clearly to S4 (intelligence/environmental adaptation) as it describes how colonial economies gather information about their environment and adapt their practices accordingly. The learning and observation processes described are quintessential intelligence functions in the VSM framework.
+
+## explanatory_value — 3.0 / 5.0
+
+The entity identifies a potentially important mechanism for colonial economic development, but remains at a fairly general level without illuminating specific causal pathways or structural relationships. It names a phenomenon that could be explanatorily valuable but doesn't develop the mechanism sufficiently to provide deep insights.