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/old_subsidy_drawback_rules.md

@@ -0,0 +1,65 @@
+---
+entity_slug: old_subsidy_drawback_rules
+evaluator: null
+evaluated_at: '2026-02-23T06:03:01.815879'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition is quite precise, specifying exact timeframes (twelve
+    months for English merchants, nine months for aliens) and clearly describing the
+    mechanism of duty recovery upon exportation. It captures a distinct regulatory
+    framework rather than a vague concept, though it could be slightly more concise.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity is clearly grounded in the actual source text from Book IV,
+    Chapter 4, which explicitly discusses the original subsidy act and its drawback
+    provisions. The specific details about timeframes and different treatment for
+    various goods directly reflect Smith's analysis of these historical regulations.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Regulation" domain assignment is perfectly appropriate, as this
+    entity describes specific administrative rules and procedures governing trade
+    policy. These drawback rules represent a clear example of governmental regulation
+    of commercial activity.
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it represents
+    the operational rules and monitoring mechanisms for duty recovery, and potentially
+    to S2 (coordination) as it standardizes procedures across different merchant categories.
+    The regulatory framework has clear VSM relevance for understanding systemic control
+    mechanisms.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: The entity provides genuine explanatory value by illuminating the specific
+    mechanisms through which drawback policies operated and evolved, showing how different
+    commodities and merchant types received differentiated treatment. It reveals structural
+    relations in trade policy administration rather than merely naming a surface phenomenon.
+---
+
+# Evaluation: Old Subsidy Drawback Rules
+
+## definition_precision — 4.0 / 5.0
+
+The definition is quite precise, specifying exact timeframes (twelve months for English merchants, nine months for aliens) and clearly describing the mechanism of duty recovery upon exportation. It captures a distinct regulatory framework rather than a vague concept, though it could be slightly more concise.
+
+## source_grounding — 5.0 / 5.0
+
+This entity is clearly grounded in the actual source text from Book IV, Chapter 4, which explicitly discusses the original subsidy act and its drawback provisions. The specific details about timeframes and different treatment for various goods directly reflect Smith's analysis of these historical regulations.
+
+## domain_placement — 5.0 / 5.0
+
+The "Regulation" domain assignment is perfectly appropriate, as this entity describes specific administrative rules and procedures governing trade policy. These drawback rules represent a clear example of governmental regulation of commercial activity.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it represents the operational rules and monitoring mechanisms for duty recovery, and potentially to S2 (coordination) as it standardizes procedures across different merchant categories. The regulatory framework has clear VSM relevance for understanding systemic control mechanisms.
+
+## explanatory_value — 4.0 / 5.0
+
+The entity provides genuine explanatory value by illuminating the specific mechanisms through which drawback policies operated and evolved, showing how different commodities and merchant types received differentiated treatment. It reveals structural relations in trade policy administration rather than merely naming a surface phenomenon.