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/coin_degradation_measurement.md

@@ -0,0 +1,63 @@
+---
+entity_slug: coin_degradation_measurement
+evaluator: null
+evaluated_at: '2026-02-23T04:43:54.844272'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition is precise and specific, providing exact quantitative
+    measures (gold >2%, silver >8% below standard weight) and clearly identifying
+    the causes of degradation. It captures a distinct measurable phenomenon rather
+    than a vague concept.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is directly grounded in Smith's text, which provides the
+    specific degradation percentages for English coins before recoinage. The figures
+    and context are explicitly stated in Book IV, Chapter 6.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Regulation" domain is perfectly appropriate, as coin degradation
+    measurement is fundamentally about monetary regulation and the need for government
+    oversight of currency standards. This fits squarely within regulatory economic
+    policy.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it represents
+    the measurement and monitoring function necessary for maintaining monetary system
+    integrity. It also connects to S2 (coordination) by providing data needed to prevent
+    monetary oscillations.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: The entity provides genuine explanatory power by quantifying the extent
+    of monetary degradation and demonstrating why recoinage was necessary. It illuminates
+    the mechanism by which poor monetary regulation leads to currency debasement and
+    economic instability.
+---
+
+# Evaluation: Coin Degradation Measurement
+
+## definition_precision — 4.0 / 5.0
+
+The definition is precise and specific, providing exact quantitative measures (gold >2%, silver >8% below standard weight) and clearly identifying the causes of degradation. It captures a distinct measurable phenomenon rather than a vague concept.
+
+## source_grounding — 5.0 / 5.0
+
+This entity is directly grounded in Smith's text, which provides the specific degradation percentages for English coins before recoinage. The figures and context are explicitly stated in Book IV, Chapter 6.
+
+## domain_placement — 5.0 / 5.0
+
+The "Regulation" domain is perfectly appropriate, as coin degradation measurement is fundamentally about monetary regulation and the need for government oversight of currency standards. This fits squarely within regulatory economic policy.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it represents the measurement and monitoring function necessary for maintaining monetary system integrity. It also connects to S2 (coordination) by providing data needed to prevent monetary oscillations.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity provides genuine explanatory power by quantifying the extent of monetary degradation and demonstrating why recoinage was necessary. It illuminates the mechanism by which poor monetary regulation leads to currency debasement and economic instability.