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/four_maxims_of_taxation.md

@@ -0,0 +1,64 @@
+---
+entity_slug: four_maxims_of_taxation
+evaluator: null
+evaluated_at: '2026-02-23T05:30:42.537670'
+overall_score: 4.8
+scores:
+- name: definition_precision
+  value: 5.0
+  max_value: 5.0
+  rationale: The definition is highly precise, clearly enumerating the four distinct
+    principles (equality, certainty, convenience, economy) with specific explanations
+    for each. This captures a well-defined conceptual framework rather than a vague
+    umbrella term.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is directly grounded in Smith's actual text from Book V,
+    Chapter 2, where he explicitly presents these four maxims as fundamental taxation
+    principles. The entity accurately reflects Smith's own systematic presentation
+    of these criteria.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"General Theory" is the appropriate domain placement since these maxims
+    constitute foundational theoretical principles that Smith applies across his entire
+    analysis of taxation systems. They represent core theoretical framework rather
+    than specific policy applications.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: These maxims map well to S3 (internal regulation/audit) as they provide
+    systematic criteria for evaluating and regulating tax systems within the economic
+    system. They also have some S5 (policy/identity) relevance as fundamental principles
+    guiding taxation policy.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides substantial explanatory power by offering the analytical
+    framework Smith uses to evaluate all taxation methods throughout his work. It
+    illuminates the underlying structural logic of his entire approach to fiscal policy
+    rather than merely naming surface phenomena.
+---
+
+# Evaluation: Four Maxims Of Taxation
+
+## definition_precision — 5.0 / 5.0
+
+The definition is highly precise, clearly enumerating the four distinct principles (equality, certainty, convenience, economy) with specific explanations for each. This captures a well-defined conceptual framework rather than a vague umbrella term.
+
+## source_grounding — 5.0 / 5.0
+
+This entity is directly grounded in Smith's actual text from Book V, Chapter 2, where he explicitly presents these four maxims as fundamental taxation principles. The entity accurately reflects Smith's own systematic presentation of these criteria.
+
+## domain_placement — 5.0 / 5.0
+
+"General Theory" is the appropriate domain placement since these maxims constitute foundational theoretical principles that Smith applies across his entire analysis of taxation systems. They represent core theoretical framework rather than specific policy applications.
+
+## vsm_relevance — 4.0 / 5.0
+
+These maxims map well to S3 (internal regulation/audit) as they provide systematic criteria for evaluating and regulating tax systems within the economic system. They also have some S5 (policy/identity) relevance as fundamental principles guiding taxation policy.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides substantial explanatory power by offering the analytical framework Smith uses to evaluate all taxation methods throughout his work. It illuminates the underlying structural logic of his entire approach to fiscal policy rather than merely naming surface phenomena.