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/colonial_economic_system_balance.md

@@ -0,0 +1,65 @@
+---
+entity_slug: colonial_economic_system_balance
+evaluator: null
+evaluated_at: '2026-02-23T04:47:37.244922'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is vague and circular, using "balance" to define "balance"
+    and listing broad economic forces without specifying what constitutes equilibrium
+    or how it's measured. It reads more like a general description than a precise
+    conceptual definition.
+- name: source_grounding
+  value: 3.0
+  max_value: 5.0
+  rationale: While Smith does discuss market mechanisms versus monopoly distortions
+    in Book IV, Chapter 7, the specific framing of "colonial economic system balance"
+    as an equilibrium concept appears to impose modern economic terminology rather
+    than reflecting Smith's actual analytical framework. Smith focuses more on the
+    effects of particular policies than on abstract balance concepts.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate given that this attempts to capture
+    Smith''s broader theoretical claims about market mechanisms and colonial policy.
+    The domain placement correctly identifies this as a theoretical rather than institutional
+    or operational concept.'
+- name: vsm_relevance
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity is too abstract and equilibrium-focused to map naturally
+    to specific VSM systems, which are about operational functions and information
+    flows. It might relate broadly to S3 (internal regulation) but lacks the structural
+    specificity that makes VSM mapping meaningful.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity merely names a surface phenomenon (economic balance) without
+    illuminating specific mechanisms or structural relations that Smith identifies.
+    It doesn't explain how balance is achieved or what specific distortions Smith
+    analyzes, reducing explanatory power to a general label.
+---
+
+# Evaluation: Colonial Economic System Balance
+
+## definition_precision — 2.0 / 5.0
+
+The definition is vague and circular, using "balance" to define "balance" and listing broad economic forces without specifying what constitutes equilibrium or how it's measured. It reads more like a general description than a precise conceptual definition.
+
+## source_grounding — 3.0 / 5.0
+
+While Smith does discuss market mechanisms versus monopoly distortions in Book IV, Chapter 7, the specific framing of "colonial economic system balance" as an equilibrium concept appears to impose modern economic terminology rather than reflecting Smith's actual analytical framework. Smith focuses more on the effects of particular policies than on abstract balance concepts.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate given that this attempts to capture Smith's broader theoretical claims about market mechanisms and colonial policy. The domain placement correctly identifies this as a theoretical rather than institutional or operational concept.
+
+## vsm_relevance — 2.0 / 5.0
+
+This entity is too abstract and equilibrium-focused to map naturally to specific VSM systems, which are about operational functions and information flows. It might relate broadly to S3 (internal regulation) but lacks the structural specificity that makes VSM mapping meaningful.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity merely names a surface phenomenon (economic balance) without illuminating specific mechanisms or structural relations that Smith identifies. It doesn't explain how balance is achieved or what specific distortions Smith analyzes, reducing explanatory power to a general label.