Triple

T6333077
Position Surface form Disambiguated ID Type / Status
Subject Maniac E142426 entity
Predicate star P23405 FINISHED
Object Sally Field E217763 NE FINISHED

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: Sally Field | Statement: [Maniac, star, Sally Field]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sally Field
Context triple: [Maniac, star, Sally Field]
  • A. Sally Field chosen
    Sally Field is an acclaimed American actress known for her versatile performances in film and television, including Oscar-winning roles in "Norma Rae" and "Places in the Heart."
  • B. Linda Hunt
    Linda Hunt is an American actress known for her Academy Award–winning role in "The Year of Living Dangerously" and for playing Hetty Lange on the television series "NCIS: Los Angeles."
  • C. Lee Grant
    Lee Grant is an Academy Award–winning American actress and director known for her powerful film and television performances and later work as a documentarian.
  • D. Susan Sarandon
    Susan Sarandon is an acclaimed American actress known for her versatile performances in film and television, including her Academy Award–winning role in "Dead Man Walking."
  • E. Shirley MacLaine
    Shirley MacLaine is an acclaimed American actress, dancer, and author known for her versatile film roles, spiritual writings, and a career spanning over six decades.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c008d4d8e88190ad301c05b08722ac completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06517a1e88190a0bfcac8a7e3a305 completed March 22, 2026, 9:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6cafb3d4c8190a00e66839c3eaf01 completed March 27, 2026, 6:22 p.m.
Created at: March 22, 2026, 4:30 p.m.