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/colony_economic_system_outcomes.md

@@ -0,0 +1,64 @@
+---
+entity_slug: colony_economic_system_outcomes
+evaluator: null
+evaluated_at: '2026-02-23T04:55:04.529955'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is vague and circular, essentially saying "outcomes are
+    results that fell short due to flaws" without specifying what constitutes these
+    outcomes or providing measurable criteria. It functions more as a general evaluative
+    statement than a precise conceptual definition.
+- name: source_grounding
+  value: 4.0
+  max_value: 5.0
+  rationale: This is well-grounded in Smith's actual analysis in Book V, Chapter 3,
+    where he systematically evaluates the disappointing results of colonial policies
+    and traces them to mercantilist misconceptions. The entity accurately reflects
+    Smith's empirical assessment of colonial economic performance.
+- name: domain_placement
+  value: 3.0
+  max_value: 5.0
+  rationale: While "Regulation" captures the policy evaluation aspect, this entity
+    spans multiple domains since it encompasses trade outcomes, fiscal results, and
+    broader economic effects. It might be better placed in a more comprehensive domain
+    like "Colonial Economics" or "Policy Analysis."
+- name: vsm_relevance
+  value: 2.0
+  max_value: 5.0
+  rationale: This entity represents evaluative outcomes rather than operational mechanisms,
+    making it difficult to map to specific VSM systems. It's more of a performance
+    assessment that could theoretically relate to S3 (audit) but lacks the structural
+    specificity that VSM analysis requires.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity merely labels disappointing results without illuminating the
+    underlying mechanisms that produced these outcomes or the structural relationships
+    between colonial policies and their effects. It describes a surface phenomenon
+    rather than explaining causal processes.
+---
+
+# Evaluation: Colony Economic System Outcomes
+
+## definition_precision — 2.0 / 5.0
+
+The definition is vague and circular, essentially saying "outcomes are results that fell short due to flaws" without specifying what constitutes these outcomes or providing measurable criteria. It functions more as a general evaluative statement than a precise conceptual definition.
+
+## source_grounding — 4.0 / 5.0
+
+This is well-grounded in Smith's actual analysis in Book V, Chapter 3, where he systematically evaluates the disappointing results of colonial policies and traces them to mercantilist misconceptions. The entity accurately reflects Smith's empirical assessment of colonial economic performance.
+
+## domain_placement — 3.0 / 5.0
+
+While "Regulation" captures the policy evaluation aspect, this entity spans multiple domains since it encompasses trade outcomes, fiscal results, and broader economic effects. It might be better placed in a more comprehensive domain like "Colonial Economics" or "Policy Analysis."
+
+## vsm_relevance — 2.0 / 5.0
+
+This entity represents evaluative outcomes rather than operational mechanisms, making it difficult to map to specific VSM systems. It's more of a performance assessment that could theoretically relate to S3 (audit) but lacks the structural specificity that VSM analysis requires.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity merely labels disappointing results without illuminating the underlying mechanisms that produced these outcomes or the structural relationships between colonial policies and their effects. It describes a surface phenomenon rather than explaining causal processes.