Triple

T21435067
Position Surface form Disambiguated ID Type / Status
Subject Judith Sutpen E528785 entity
Predicate hasRelative P367 FINISHED
Object Rosa Coldfield 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: Rosa Coldfield | Statement: [Judith Sutpen, hasRelative, Rosa Coldfield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rosa Coldfield
Context triple: [Judith Sutpen, hasRelative, Rosa Coldfield]
  • A. Rosa Coldfield chosen
    Rosa Coldfield is a central figure in William Faulkner’s novel *Absalom, Absalom!*, serving as one of the primary narrators whose recollections help unravel the tragic history of the Sutpen family.
  • B. Rosa Rhodes
    Rosa Rhodes is known as the wife of geologist and former Cornell University president Frank H. T. Rhodes.
  • C. Lucinda Ashby
    Lucinda Ashby is an Episcopal bishop who leads the Diocese of El Camino Real in California.
  • D. Rosemary Thorpe
    Rosemary Thorpe is a person notable enough to be recognized as a significant bearer of the surname Thorpe.
  • E. Rosalie Booth
    Rosalie Booth was a 19th-century American woman best known as a member of the prominent Booth theatrical family, which included several famous stage actors.
  • 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_69e0c4569fa081908101baa24f8745db completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69e8b536274c8190809bd3cdf4ef899e completed April 22, 2026, 11:47 a.m.
Created at: April 16, 2026, 6:02 p.m.