Triple

T16627993
Position Surface form Disambiguated ID Type / Status
Subject Ghost E404000 entity
Predicate producer P490 FINISHED
Object Lisa Weinstein 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: Lisa Weinstein | Statement: [Ghost, producer, Lisa Weinstein]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lisa Weinstein
Context triple: [Ghost, producer, Lisa Weinstein]
  • A. Lisa Weinstein chosen
    Lisa Weinstein is a film producer best known for her work on the acclaimed 1990 romantic fantasy drama "Ghost."
  • B. Emma Weinstein
    Emma Weinstein is one of the daughters of disgraced Hollywood film producer Harvey Weinstein.
  • C. Rachel Leibowitz
    Rachel Leibowitz is a person notable enough to be specifically cited as a bearer of the surname Leibowitz.
  • D. Juliana Hatkoff
    Juliana Hatkoff is a children's book coauthor known for collaborating with her father, investor and philanthropist Craig Hatkoff, on inspirational animal stories.
  • E. Jennifer Weiss
    Jennifer Weiss is a film producer known for her work on independent movies, including the Canadian drama "Take This Waltz."
  • 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_69d883897eb481909eaaa088ba9918d9 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e378e2683481908c9a5ed895a09a6e completed April 18, 2026, 12:28 p.m.
Created at: April 10, 2026, 5:17 a.m.