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_outcomes.md

@@ -0,0 +1,65 @@
+---
+entity_slug: colonial_economic_system_outcomes
+evaluator: null
+evaluated_at: '2026-02-23T04:49:37.414816'
+overall_score: 3.8
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a distinct concept about comparative outcomes
+    of colonial policies, but uses somewhat vague terms like "better outcomes" and
+    "suboptimal results" without precise metrics. It clearly distinguishes between
+    monopoly and open systems but could be more specific about what constitutes these
+    outcomes.
+- name: source_grounding
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity is well-grounded in Smith's actual analysis in Book IV, Chapter
+    7, where he extensively compares different colonial management approaches and
+    their results. Smith does indeed argue that monopolistic colonial policies produce
+    worse outcomes than more open arrangements.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate as this entity represents Smith''s broader
+    theoretical conclusions about colonial policy effectiveness rather than specific
+    mechanisms or historical examples. It synthesizes his comparative analysis into
+    general principles about economic system design.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it represents
+    the evaluation and measurement of system performance outcomes. It also has S4
+    relevance as it involves learning from environmental feedback about which policies
+    work better in practice.
+- name: explanatory_value
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity provides significant explanatory value by illuminating the
+    structural relationship between policy design (monopoly vs. open systems) and
+    systemic outcomes. It reveals a key mechanism in Smith's argument about how institutional
+    arrangements determine economic performance.
+---
+
+# Evaluation: Colonial Economic System Outcomes
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a distinct concept about comparative outcomes of colonial policies, but uses somewhat vague terms like "better outcomes" and "suboptimal results" without precise metrics. It clearly distinguishes between monopoly and open systems but could be more specific about what constitutes these outcomes.
+
+## source_grounding — 4.0 / 5.0
+
+This entity is well-grounded in Smith's actual analysis in Book IV, Chapter 7, where he extensively compares different colonial management approaches and their results. Smith does indeed argue that monopolistic colonial policies produce worse outcomes than more open arrangements.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate as this entity represents Smith's broader theoretical conclusions about colonial policy effectiveness rather than specific mechanisms or historical examples. It synthesizes his comparative analysis into general principles about economic system design.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it represents the evaluation and measurement of system performance outcomes. It also has S4 relevance as it involves learning from environmental feedback about which policies work better in practice.
+
+## explanatory_value — 4.0 / 5.0
+
+This entity provides significant explanatory value by illuminating the structural relationship between policy design (monopoly vs. open systems) and systemic outcomes. It reveals a key mechanism in Smith's argument about how institutional arrangements determine economic performance.