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_success_measure.md

@@ -0,0 +1,63 @@
+---
+entity_slug: economic_system_success_measure
+evaluator: null
+evaluated_at: '2026-02-23T05:21:12.579993'
+overall_score: 3.0
+scores:
+- name: definition_precision
+  value: 3.0
+  max_value: 5.0
+  rationale: The definition captures a coherent concept about measuring economic system
+    performance, but it's somewhat broad and could be more precise about what constitutes
+    "success" versus mere measurement. The inclusion of both wealth generation and
+    distribution metrics adds useful specificity.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss the objectives of political economy (providing
+    subsistence and revenue), he doesn't explicitly develop a framework for measuring
+    system success or performance indicators. This entity extrapolates beyond what
+    Smith directly addresses in the text.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: '"General Theory" is appropriate since this concept would span across
+    Smith''s various discussions of different economic systems and policies. It''s
+    meta-analytical rather than tied to specific mechanisms like trade or production.'
+- name: vsm_relevance
+  value: 4.0
+  max_value: 5.0
+  rationale: This entity maps well to S3 (internal regulation/audit) as it concerns
+    monitoring and evaluating system performance against objectives. It could also
+    relate to S5 (identity/policy) in terms of defining what constitutes successful
+    achievement of the system's purpose.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: While the concept of measuring economic success is important, this entity
+    doesn't illuminate specific mechanisms or structural relations that Smith explores.
+    It's more of a meta-concept that names the need for evaluation rather than explaining
+    how economic systems actually function.
+---
+
+# Evaluation: Economic System Success Measure
+
+## definition_precision — 3.0 / 5.0
+
+The definition captures a coherent concept about measuring economic system performance, but it's somewhat broad and could be more precise about what constitutes "success" versus mere measurement. The inclusion of both wealth generation and distribution metrics adds useful specificity.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss the objectives of political economy (providing subsistence and revenue), he doesn't explicitly develop a framework for measuring system success or performance indicators. This entity extrapolates beyond what Smith directly addresses in the text.
+
+## domain_placement — 4.0 / 5.0
+
+"General Theory" is appropriate since this concept would span across Smith's various discussions of different economic systems and policies. It's meta-analytical rather than tied to specific mechanisms like trade or production.
+
+## vsm_relevance — 4.0 / 5.0
+
+This entity maps well to S3 (internal regulation/audit) as it concerns monitoring and evaluating system performance against objectives. It could also relate to S5 (identity/policy) in terms of defining what constitutes successful achievement of the system's purpose.
+
+## explanatory_value — 2.0 / 5.0
+
+While the concept of measuring economic success is important, this entity doesn't illuminate specific mechanisms or structural relations that Smith explores. It's more of a meta-concept that names the need for evaluation rather than explaining how economic systems actually function.