Triple

T17902811
Position Surface form Disambiguated ID Type / Status
Subject David Fisher E447625 entity
Predicate relative P37 FINISHED
Object Ruth Fisher NE NERFINISHED

How this triple was built (2 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Ruth Fisher | Statement: [David Fisher, relative, Ruth Fisher]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ruth Fisher
Context triple: [David Fisher, relative, Ruth Fisher]
  • A. Ruth Fisher chosen
    Ruth Fisher is a central character in the television drama "Six Feet Under," portrayed as the emotionally complex matriarch of the Fisher family who struggles with grief, identity, and independence.
  • B. Ruth Batchelor
    Ruth Batchelor was an American songwriter, music journalist, and prominent advocate for songwriters’ rights, known for co-founding the Los Angeles Songwriters Showcase.
  • C. Ruth Cosgrove
    Ruth Cosgrove was the wife of American comedian and television pioneer Milton Berle.
  • D. Ruth Riley
    Ruth Riley is a former American professional basketball center best known for starring at Notre Dame and winning WNBA championships and a Finals MVP award with the Detroit Shock.
  • E. Ruth Myers
    Ruth Myers is an acclaimed British costume designer known for her imaginative and character-defining work on numerous films and television productions.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e99c3188190aead24cd3d48c7a7 completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.