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/measure_of_exchangeable_value.md

@@ -0,0 +1,64 @@
+---
+entity_slug: measure_of_exchangeable_value
+evaluator: null
+evaluated_at: '2026-02-23T05:49:58.440923'
+overall_score: 4.4
+scores:
+- name: definition_precision
+  value: 4.0
+  max_value: 5.0
+  rationale: The definition clearly identifies labour as the universal standard for
+    comparing commodity values across time and space. While precise in identifying
+    labour as the measure, it could be slightly more specific about what aspect of
+    labour (quantity, time, etc.) constitutes the measure.
+- name: source_grounding
+  value: 5.0
+  max_value: 5.0
+  rationale: This concept is directly and extensively grounded in Book I, Chapter
+    5 of The Wealth of Nations, where Smith explicitly argues that labour is the real
+    measure of exchangeable value. The entity accurately reflects Smith's central
+    argument in this foundational chapter on value theory.
+- name: domain_placement
+  value: 5.0
+  max_value: 5.0
+  rationale: The "Exchange" domain is perfectly appropriate since this concept deals
+    fundamentally with how commodities are valued relative to each other in market
+    transactions. This is core exchange theory rather than production, distribution,
+    or consumption.
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: This concept has moderate VSM relevance as a foundational measurement
+    standard that could inform multiple systems, particularly S3 (internal regulation
+    through value assessment) and S4 (intelligence gathering about relative values).
+    However, it's more of an analytical tool than an operational system component.
+- name: explanatory_value
+  value: 5.0
+  max_value: 5.0
+  rationale: This entity provides exceptional explanatory power by identifying the
+    fundamental mechanism through which economic actors can compare disparate goods
+    across different contexts. It illuminates how market exchange becomes possible
+    through a universal value standard rather than just naming a surface phenomenon.
+---
+
+# Evaluation: Measure Of Exchangeable Value
+
+## definition_precision — 4.0 / 5.0
+
+The definition clearly identifies labour as the universal standard for comparing commodity values across time and space. While precise in identifying labour as the measure, it could be slightly more specific about what aspect of labour (quantity, time, etc.) constitutes the measure.
+
+## source_grounding — 5.0 / 5.0
+
+This concept is directly and extensively grounded in Book I, Chapter 5 of The Wealth of Nations, where Smith explicitly argues that labour is the real measure of exchangeable value. The entity accurately reflects Smith's central argument in this foundational chapter on value theory.
+
+## domain_placement — 5.0 / 5.0
+
+The "Exchange" domain is perfectly appropriate since this concept deals fundamentally with how commodities are valued relative to each other in market transactions. This is core exchange theory rather than production, distribution, or consumption.
+
+## vsm_relevance — 3.0 / 5.0
+
+This concept has moderate VSM relevance as a foundational measurement standard that could inform multiple systems, particularly S3 (internal regulation through value assessment) and S4 (intelligence gathering about relative values). However, it's more of an analytical tool than an operational system component.
+
+## explanatory_value — 5.0 / 5.0
+
+This entity provides exceptional explanatory power by identifying the fundamental mechanism through which economic actors can compare disparate goods across different contexts. It illuminates how market exchange becomes possible through a universal value standard rather than just naming a surface phenomenon.