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/taille.md

@@ -0,0 +1,64 @@
+---
+entity_slug: taille
+evaluator: null
+evaluated_at: '2026-02-23T06:28:57.228034'
+overall_score: 4.6
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly specifies the taille as a French land tax based
+    on supposed profits from farm stock, with well-articulated perverse incentives.
+    It's precise and non-circular, though could benefit from slightly more detail
+    about the assessment mechanism.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This is directly grounded in Smith's text from Book III, Chapter 2, where
+    he explicitly discusses the taille as a problematic French tax system. The description
+    of its effects on cultivation and investment aligns closely with Smith's analysis.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: '"Regulation" is the correct domain placement, as the taille represents
+    a specific regulatory mechanism (taxation) that creates systematic economic distortions.
+    It fits perfectly within Smith''s broader analysis of how regulatory frameworks
+    affect economic behavior.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This maps well to S3 (internal regulation/audit) as a regulatory mechanism
+    that's supposed to monitor and extract value from economic activity, though it's
+    a dysfunctional one. It also touches on S4 concerns about how regulatory systems
+    adapt (or fail to adapt) to economic realities.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity illuminates a crucial mechanism showing how tax design creates
+    systematic incentives that distort economic behavior, serving as a concrete example
+    of Smith's broader principles about the relationship between institutional design
+    and economic outcomes. It demonstrates structural causation rather than just naming
+    a phenomenon.
+---
+
+# Evaluation: Taille
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly specifies the taille as a French land tax based on supposed profits from farm stock, with well-articulated perverse incentives. It's precise and non-circular, though could benefit from slightly more detail about the assessment mechanism.
+
+## source_grounding — 5.0 / 5.0
+
+This is directly grounded in Smith's text from Book III, Chapter 2, where he explicitly discusses the taille as a problematic French tax system. The description of its effects on cultivation and investment aligns closely with Smith's analysis.
+
+## domain_placement — 5.0 / 5.0
+
+"Regulation" is the correct domain placement, as the taille represents a specific regulatory mechanism (taxation) that creates systematic economic distortions. It fits perfectly within Smith's broader analysis of how regulatory frameworks affect economic behavior.
+
+## vsm_relevance — 4.0 / 5.0
+
+This maps well to S3 (internal regulation/audit) as a regulatory mechanism that's supposed to monitor and extract value from economic activity, though it's a dysfunctional one. It also touches on S4 concerns about how regulatory systems adapt (or fail to adapt) to economic realities.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity illuminates a crucial mechanism showing how tax design creates systematic incentives that distort economic behavior, serving as a concrete example of Smith's broader principles about the relationship between institutional design and economic outcomes. It demonstrates structural causation rather than just naming a phenomenon.