Triple

T22223779
Position Surface form Disambiguated ID Type / Status
Subject Norma Deloris Egstrom E549279 entity
Predicate child P120 FINISHED
Object Nicki Lee Foster 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: Nicki Lee Foster | Statement: [Norma Deloris Egstrom, child, Nicki Lee Foster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicki Lee Foster
Context triple: [Norma Deloris Egstrom, child, Nicki Lee Foster]
  • A. Nicki Lee Foster chosen
    Nicki Lee Foster is the daughter of legendary American singer and actress Peggy Lee.
  • B. Minnie Driver
    Minnie Driver is a British-American actress and singer best known for her acclaimed, Oscar-nominated performance in the film "Good Will Hunting."
  • C. Diana Kerry
    Diana Kerry is a member of the prominent American political Kerry family, known for its long-standing involvement in public service and diplomacy.
  • D. Mary Sean Young
    Mary Sean Young is an American actress best known for her roles in films such as "Blade Runner," "Dune," and "No Way Out."
  • E. Judy Foster
    Judy Foster is the lively, boy-crazy teenage heroine of the radio, film, and comic series "A Date with Judy," known for her humorous misadventures in romance and family life.
  • 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_69e11e403d6481909a94d0aaf157f6ef completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12b92b79c8190a8a4d33591abd763 completed April 28, 2026, 9:50 p.m.
Created at: April 16, 2026, 8:37 p.m.