Triple

T17757578
Position Surface form Disambiguated ID Type / Status
Subject Amy Ephron E443283 entity
Predicate spouse P13 FINISHED
Object Alan F. Horn 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: Alan F. Horn | Statement: [Amy Ephron, spouse, Alan F. Horn]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alan F. Horn
Context triple: [Amy Ephron, spouse, Alan F. Horn]
  • A. Alan Horn chosen
    Alan Horn is an American film executive and producer best known for co-founding Castle Rock Entertainment and leading major studios such as Warner Bros. and Walt Disney Studios.
  • B. John Felstiner
    John Felstiner was an American literary scholar, critic, and translator best known for his influential English translations and critical studies of German-language poet Paul Celan.
  • C. Michael Eisner
    Michael Eisner is an American businessman and former longtime CEO of The Walt Disney Company, known for overseeing its major expansion in the late 20th century.
  • D. Gerald Levin
    Gerald Levin is an American media executive best known for leading Time Warner as CEO and orchestrating its landmark merger with AOL.
  • E. Peter Guber
    Peter Guber is an American film producer, entrepreneur, and sports team owner known for his leadership roles with major franchises like the Los Angeles Dodgers and Golden State Warriors.
  • 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_69d8b9edf16c8190a59ebd245d378f4f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841fe97881908f4df503fb781763 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.