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_best_practice.md

@@ -0,0 +1,64 @@
+---
+entity_slug: economic_system_best_practice
+evaluator: null
+evaluated_at: '2026-02-23T05:13:16.600470'
+overall_score: 2.2
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is vague and circular, essentially defining "best practice"
+    as "most effective approaches" without clear criteria for what constitutes effectiveness
+    or success. It reads more like a generic business term than a precise economic
+    concept with distinct boundaries.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does compare different economic systems and their merits,
+    he doesn't explicitly develop a concept of "best practices" as a distinct analytical
+    category. This appears to impose modern management terminology onto Smith's more
+    nuanced discussions of systemic advantages and disadvantages.
+- name: domain_placement
+  value: 3.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate given the broad, cross-cutting nature
+    of the concept, though the entity itself may be too abstract to warrant domain
+    placement. The assignment doesn''t clearly misplace the concept but reflects its
+    lack of specificity.'
+- name: vsm_relevance
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity is too abstract and meta-level to map meaningfully to specific
+    VSM systems - it could theoretically apply to any system (S1-S5) but doesn't illuminate
+    the particular functions or mechanisms of any. It lacks the operational specificity
+    needed for VSM mapping.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity provides minimal explanatory power, functioning more as a
+    label than revealing underlying economic mechanisms or structural relationships.
+    It doesn't help understand how economic systems actually work or what makes particular
+    arrangements effective.
+---
+
+# Evaluation: Economic System Best Practice
+
+## definition_precision — 2.0 / 5.0
+
+The definition is vague and circular, essentially defining "best practice" as "most effective approaches" without clear criteria for what constitutes effectiveness or success. It reads more like a generic business term than a precise economic concept with distinct boundaries.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does compare different economic systems and their merits, he doesn't explicitly develop a concept of "best practices" as a distinct analytical category. This appears to impose modern management terminology onto Smith's more nuanced discussions of systemic advantages and disadvantages.
+
+## domain_placement — 3.0 / 5.0
+
+"General Theory" is appropriate given the broad, cross-cutting nature of the concept, though the entity itself may be too abstract to warrant domain placement. The assignment doesn't clearly misplace the concept but reflects its lack of specificity.
+
+## vsm_relevance — 2.0 / 5.0
+
+This entity is too abstract and meta-level to map meaningfully to specific VSM systems - it could theoretically apply to any system (S1-S5) but doesn't illuminate the particular functions or mechanisms of any. It lacks the operational specificity needed for VSM mapping.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity provides minimal explanatory power, functioning more as a label than revealing underlying economic mechanisms or structural relationships. It doesn't help understand how economic systems actually work or what makes particular arrangements effective.