Triple

T22753778
Position Surface form Disambiguated ID Type / Status
Subject Jane Wolfe E562779 entity
Predicate name P16 FINISHED
Object Jane Wolfe 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: Jane Wolfe | Statement: [Jane Wolfe, name, Jane Wolfe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jane Wolfe
Context triple: [Jane Wolfe, name, Jane Wolfe]
  • A. Jane Wolfe chosen
    Jane Wolfe was an American silent film actress best known for her early 20th-century screen roles and later association with occultist Aleister Crowley.
  • B. Rosemary Wolff
    Rosemary Wolff is the mother of American memoirist and novelist Tobias Wolff, known from his autobiographical work "This Boy's Life."
  • C. Ann Wolfe
    Ann Wolfe is a former American professional boxer renowned for her formidable punching power and multiple world titles across several weight classes.
  • D. Amy Lindley
    Amy Lindley is a fictional character from the television series "Dawson's Creek," known as the daughter of Jen Lindley.
  • E. Beth Willman
    Beth Willman is an American astronomer known for her work on faint dwarf galaxies and the structure of the Milky Way’s satellite system.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179bb80ac8190b53a1e00704c4ff5 completed April 29, 2026, 3:23 a.m.
Created at: April 17, 2026, 3:25 p.m.