feat(example): add L2 classifications for 823/988 WoN entities (S3.4)

Batch classification via OpenRouter (claude-sonnet-4). 165 entities
remain unclassified due to credit exhaustion; incremental skip means
a follow-up run will complete them automatically.

Type × VSM matrix (823 entities):
                  S1   S2   S3  S3*   S4   S5
  Element         86   75   58   21   43   32  (315 total, 38%)
  Process         39   42   37   17   67   24  (226 total, 28%)
  Institution      4   12   30   24    .   52  (122 total, 15%)
  Principle        3    7   15    2   43   32  (102 total, 12%)
  Relation         2   14    5    5   22   10   (58 total,  7%)
  Matrix fill: 29/30 cells (Institution/S4 empty — expected)

Metrics updated: type_entropy=2.0936, vsm_type_matrix_cells=29

Also:
- BatchEvaluator gains delay_seconds param for rate-limited providers
- classify CLI gains --rpm option (--rpm 10 for Gemini free tier)
- history.write_metrics_file now handles non-float metric values
  (type_distribution is a dict, was crashing round())
- run_entity_classification forwards delay_seconds to BatchEvaluator
- classify-links and graph commands added by user (entities --by-type,
  graph --format mermaid/dot, classify-links for Relation enrichment)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-23 12:49:11 +01:00
parent a9ca0adfcf
commit d1f57272a4
827 changed files with 25240 additions and 4 deletions

View File

@@ -32,6 +32,13 @@ class EntityClassification:
classified_by: str = "" # model name
classified_at: Optional[datetime] = None
# Optional — only set when entity_type == "Relation"
links_subject: str = "" # human-readable title of entity A
links_subject_slug: str = "" # slug of entity A
links_object: str = "" # human-readable title of entity B
links_object_slug: str = "" # slug of entity B
links_mechanism: str = "" # one sentence: how A and B are connected
def to_dict(self) -> Dict[str, Any]:
d: Dict[str, Any] = {
"entity_slug": self.entity_slug,
@@ -46,6 +53,16 @@ class EntityClassification:
d["classified_by"] = self.classified_by
if self.classified_at is not None:
d["classified_at"] = self.classified_at.isoformat()
if self.links_subject:
d["links_subject"] = self.links_subject
if self.links_subject_slug:
d["links_subject_slug"] = self.links_subject_slug
if self.links_object:
d["links_object"] = self.links_object
if self.links_object_slug:
d["links_object_slug"] = self.links_object_slug
if self.links_mechanism:
d["links_mechanism"] = self.links_mechanism
return d
@classmethod
@@ -61,4 +78,9 @@ class EntityClassification:
vsm_rationale=data.get("vsm_rationale", ""),
classified_by=data.get("classified_by", ""),
classified_at=classified_at,
links_subject=data.get("links_subject", ""),
links_subject_slug=data.get("links_subject_slug", ""),
links_object=data.get("links_object", ""),
links_object_slug=data.get("links_object_slug", ""),
links_mechanism=data.get("links_mechanism", ""),
)