Triple

T18181425
Position Surface form Disambiguated ID Type / Status
Subject Michael Eisner E435292 entity
Predicate hasChild P369 FINISHED
Object Eric Eisner 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: Eric Eisner | Statement: [Michael Eisner, hasChild, Eric Eisner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Eric Eisner
Context triple: [Michael Eisner, hasChild, Eric Eisner]
  • A. Eric Eisner chosen
    Eric Eisner is a film producer best known for his work on independent and offbeat movies, including the comedy "Hamlet 2."
  • B. Ron Burkle
    Ron Burkle is an American billionaire investor and co-founder of the private equity firm Yucaipa Companies, known for his extensive investments in retail, sports, and media.
  • C. Rich Silverstein
    Rich Silverstein is an influential American advertising executive and co-founder of the agency Goodby, Silverstein & Partners, known for iconic campaigns such as “Got Milk?”.
  • D. Larry Eisenberg
    Larry Eisenberg was an American biomedical engineer, science fiction writer, and humorist best known for his witty limericks and contributions to speculative fiction.
  • E. Terry Semel
    Terry Semel is an American media executive best known as the former CEO and Chairman of Yahoo! and longtime Warner Bros. studio chief.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dffb3bc88190a627be9c444d5c7d completed April 19, 2026, 2 p.m.
Created at: April 10, 2026, 10:31 a.m.