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/bank_economic_contribution_metrics.md

@@ -0,0 +1,66 @@
+---
+entity_slug: bank_economic_contribution_metrics
+evaluator: null
+evaluated_at: '2026-02-23T00:38:15.927331'
+overall_score: 2.6
+scores:
+- name: definition_precision
+  value: 2.0
+  max_value: 5.0
+  rationale: The definition is vague and umbrella-like, listing broad categories ("capital
+    allocation efficiency, transaction cost reduction, and financial innovation impact")
+    without clearly defining what constitutes these metrics or how they're measured.
+    It reads more like a modern economic framework than a precise concept from Smith's
+    work.
+- name: source_grounding
+  value: 2.0
+  max_value: 5.0
+  rationale: While Smith does discuss banking's role in economic development in Book
+    II, Chapter 2, he doesn't present a systematic framework of "metrics" for evaluating
+    banking contribution in the modern sense described here. This appears to impose
+    contemporary economic measurement concepts onto Smith's more descriptive analysis.
+- name: domain_placement
+  value: 4.0
+  max_value: 5.0
+  rationale: The "Accumulation" domain is appropriate since Smith's discussion of
+    banking in Book II, Chapter 2 focuses on how banks facilitate capital accumulation
+    and productive investment. The entity correctly identifies this as part of the
+    capital formation process.
+- name: vsm_relevance
+  value: 3.0
+  max_value: 5.0
+  rationale: This entity could map to S3 (internal regulation/audit) as it involves
+    measurement and evaluation systems, but it's somewhat abstract and doesn't clearly
+    represent an operational system component. The metrics concept is more of a meta-analytical
+    tool than a direct VSM system.
+- name: explanatory_value
+  value: 2.0
+  max_value: 5.0
+  rationale: The entity doesn't illuminate specific mechanisms or structural relations
+    from Smith's analysis, instead creating a modern analytical overlay that obscures
+    rather than clarifies Smith's actual insights about how banking functions in the
+    economy. It names a surface phenomenon without explaining underlying economic
+    processes.
+---
+
+# Evaluation: Bank Economic Contribution Metrics
+
+## definition_precision — 2.0 / 5.0
+
+The definition is vague and umbrella-like, listing broad categories ("capital allocation efficiency, transaction cost reduction, and financial innovation impact") without clearly defining what constitutes these metrics or how they're measured. It reads more like a modern economic framework than a precise concept from Smith's work.
+
+## source_grounding — 2.0 / 5.0
+
+While Smith does discuss banking's role in economic development in Book II, Chapter 2, he doesn't present a systematic framework of "metrics" for evaluating banking contribution in the modern sense described here. This appears to impose contemporary economic measurement concepts onto Smith's more descriptive analysis.
+
+## domain_placement — 4.0 / 5.0
+
+The "Accumulation" domain is appropriate since Smith's discussion of banking in Book II, Chapter 2 focuses on how banks facilitate capital accumulation and productive investment. The entity correctly identifies this as part of the capital formation process.
+
+## vsm_relevance — 3.0 / 5.0
+
+This entity could map to S3 (internal regulation/audit) as it involves measurement and evaluation systems, but it's somewhat abstract and doesn't clearly represent an operational system component. The metrics concept is more of a meta-analytical tool than a direct VSM system.
+
+## explanatory_value — 2.0 / 5.0
+
+The entity doesn't illuminate specific mechanisms or structural relations from Smith's analysis, instead creating a modern analytical overlay that obscures rather than clarifies Smith's actual insights about how banking functions in the economy. It names a surface phenomenon without explaining underlying economic processes.