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_evaluation.md

@@ -0,0 +1,65 @@
+---
+entity_slug: economic_system_evaluation
+evaluator: null
+evaluated_at: '2026-02-23T05:15:29.540817'
+overall_score: 3.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a coherent concept but remains somewhat broad
+    and umbrella-like. While it identifies specific criteria (outcomes, effectiveness,
+    achieving political economy objectives), it could be more precise about what constitutes
+    "assessment" versus other forms of analysis.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith certainly evaluates different economic systems throughout
+    the work, he doesn't explicitly articulate a formal framework for "economic system
+    evaluation" as a distinct methodological concept. This appears to be an analytical
+    abstraction imposed on Smith's comparative discussions rather than a concept he
+    directly presents.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate since this represents a meta-analytical
+    framework that would apply across Smith''s various discussions of mercantilism,
+    physiocracy, and natural liberty. It''s correctly positioned as a theoretical
+    tool rather than a specific economic mechanism.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This maps well to S3 (internal regulation/audit) as it represents the
+    monitoring and assessment function that evaluates system performance against objectives.
+    It could also relate to S4 (intelligence) in terms of learning from different
+    system outcomes.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity names Smith's comparative methodology but doesn't illuminate
+    specific mechanisms or structural relations within economic systems themselves.
+    It's more of a meta-commentary on Smith's analytical approach than a substantive
+    economic concept that advances understanding of wealth creation.
+---
+
+# Evaluation: Economic System Evaluation
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a coherent concept but remains somewhat broad and umbrella-like. While it identifies specific criteria (outcomes, effectiveness, achieving political economy objectives), it could be more precise about what constitutes "assessment" versus other forms of analysis.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith certainly evaluates different economic systems throughout the work, he doesn't explicitly articulate a formal framework for "economic system evaluation" as a distinct methodological concept. This appears to be an analytical abstraction imposed on Smith's comparative discussions rather than a concept he directly presents.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate since this represents a meta-analytical framework that would apply across Smith's various discussions of mercantilism, physiocracy, and natural liberty. It's correctly positioned as a theoretical tool rather than a specific economic mechanism.
+
+## vsm_relevance — 4.0 / 5.0
+
+This maps well to S3 (internal regulation/audit) as it represents the monitoring and assessment function that evaluates system performance against objectives. It could also relate to S4 (intelligence) in terms of learning from different system outcomes.
+
+## explanatory_value — 2.0 / 5.0
+
+This entity names Smith's comparative methodology but doesn't illuminate specific mechanisms or structural relations within economic systems themselves. It's more of a meta-commentary on Smith's analytical approach than a substantive economic concept that advances understanding of wealth creation.