2.1 KiB
Entity And Relation Model
infospace-bench owns the application-level semantic model for infospace
entities and relation triplets. markitect-tool remains the Markdown structure
provider and is accessed only through infospace_bench.markdown_adapter.
Entity Artifacts
Entity artifacts are registered in artifacts/index.yaml with kind: entity
and are stored under artifacts/entities/.
The parser extracts:
artifact_id: manifest identity such asentity/division.mdslug,title, andh1_raw: identity derived from the document H1definition,source_chapter,context,domain,original_wording, andmodern_interpretation: legacy-style sections where presenth1_is_title_case,has_original_wording,definition_word_count,total_word_count, and orderedsection_slugs: compatibility metrics used by evaluation and inspection flowssource_path: path to the concrete artifact file
## Definition is required. Missing required sections raise
invalid_entity_artifact with a missing_sections detail list.
Relation Artifacts
Relation artifacts are registered with kind: relation and are stored under
artifacts/relations/.
The parser extracts:
artifact_idandslug: manifest identity plus a relation slug derived from the H1subject,predicate,object: the relation tripletsubject_slug,object_slug,subject_entity_id, andobject_entity_id: endpoint links back to parsed entity artifactsrelation_type,vsm_channel,evidence, andfeedback_role: semantic and evaluation metadatais_feedback_member: derived from whetherfeedback_roleis present
## Subject, ## Predicate, and ## Object are required. When relation
listing is performed from an infospace manifest, subject and object slugs must
resolve to entity artifacts or unresolved_relation_endpoint is raised.
CLI
python3 -m infospace_bench entities infospaces/bootstrap-pilot
python3 -m infospace_bench relations infospaces/bootstrap-pilot
These commands emit JSON records for downstream evaluation, graphing, and inspection workflows.