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/economic_system_mechanism.md

@@ -0,0 +1,63 @@
+---
+entity_slug: economic_system_mechanism
+evaluator: null
+evaluated_at: '2026-02-23T05:18:41.111398'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is overly broad and circular, essentially defining "mechanism"
+    as "processes and methods through which things function." It lacks the precision
+    needed to distinguish this concept from general economic processes or systems
+    themselves.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss different economic systems and their operations,
+    this entity appears to be a modern analytical abstraction rather than a concept
+    Smith explicitly articulates. The reference to "Book IV, Chapter 0" is also problematic
+    as chapters typically don't start at zero.
+- name: domain_placement
+  value: 3.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate given the broad, meta-analytical nature
+    of this concept. However, the entity is so abstract that it doesn''t clearly belong
+    to any specific economic domain that Smith would recognize.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity has strong VSM relevance as it directly addresses operational
+    mechanisms, which could map across multiple VSM systems (S1 operations, S2 coordination,
+    S3 regulation). The focus on "how things work" aligns well with VSM's systemic
+    perspective.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: "The entity adds little explanatory value because it's too generic\u2014\
+    it names the idea of mechanisms without illuminating any specific mechanism or\
+    \ providing analytical insight. It functions more as a meta-category than an explanatory\
+    \ concept."
+---
+
+# Evaluation: Economic System Mechanism
+
+## definition_precision — 2.0 / 5.0
+
+The definition is overly broad and circular, essentially defining "mechanism" as "processes and methods through which things function." It lacks the precision needed to distinguish this concept from general economic processes or systems themselves.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss different economic systems and their operations, this entity appears to be a modern analytical abstraction rather than a concept Smith explicitly articulates. The reference to "Book IV, Chapter 0" is also problematic as chapters typically don't start at zero.
+
+## domain_placement — 3.0 / 5.0
+
+"General Theory" is appropriate given the broad, meta-analytical nature of this concept. However, the entity is so abstract that it doesn't clearly belong to any specific economic domain that Smith would recognize.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity has strong VSM relevance as it directly addresses operational mechanisms, which could map across multiple VSM systems (S1 operations, S2 coordination, S3 regulation). The focus on "how things work" aligns well with VSM's systemic perspective.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity adds little explanatory value because it's too generic—it names the idea of mechanisms without illuminating any specific mechanism or providing analytical insight. It functions more as a meta-category than an explanatory concept.