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_efficiency.md

@@ -0,0 +1,63 @@
+---
+entity_slug: economic_system_efficiency
+evaluator: null
+evaluated_at: '2026-02-23T05:15:10.930901'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a coherent concept about resource allocation
+    and productivity, but it's somewhat broad and could apply to almost any economic
+    arrangement. The phrase "achieve their objectives" is vague since different systems
+    may have different objectives.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity acknowledges that efficiency is "not explicitly discussed
+    by Smith in this chapter" and is only "implied," which suggests weak grounding
+    in the actual source text. This appears to be imposing a modern economic concept
+    onto Smith's work rather than extracting what he actually wrote.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is an appropriate domain for a broad concept about
+    how economic systems function overall. The concept does relate to fundamental
+    questions about economic arrangements that Smith addresses throughout his work.'
+- name: vsm_relevance
+  value: 2.0
+  max_value: 5.0
+  rationale: This concept is too abstract and general to map naturally to specific
+    VSM systems - it could theoretically apply to any system (S1-S5) since all systems
+    should operate efficiently. It lacks the structural specificity needed for meaningful
+    VSM placement.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: While efficiency is an important economic concept, this entity doesn't
+    illuminate specific mechanisms or structural relations from Smith's analysis.
+    It's more of a general evaluative criterion than an explanatory concept that reveals
+    how economic systems actually work.
+---
+
+# Evaluation: Economic System Efficiency
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a coherent concept about resource allocation and productivity, but it's somewhat broad and could apply to almost any economic arrangement. The phrase "achieve their objectives" is vague since different systems may have different objectives.
+
+## source_grounding — 2.0 / 5.0
+
+The entity acknowledges that efficiency is "not explicitly discussed by Smith in this chapter" and is only "implied," which suggests weak grounding in the actual source text. This appears to be imposing a modern economic concept onto Smith's work rather than extracting what he actually wrote.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is an appropriate domain for a broad concept about how economic systems function overall. The concept does relate to fundamental questions about economic arrangements that Smith addresses throughout his work.
+
+## vsm_relevance — 2.0 / 5.0
+
+This concept is too abstract and general to map naturally to specific VSM systems - it could theoretically apply to any system (S1-S5) since all systems should operate efficiently. It lacks the structural specificity needed for meaningful VSM placement.
+
+## explanatory_value — 2.0 / 5.0
+
+While efficiency is an important economic concept, this entity doesn't illuminate specific mechanisms or structural relations from Smith's analysis. It's more of a general evaluative criterion than an explanatory concept that reveals how economic systems actually work.