Triple

T7494636
Position Surface form Disambiguated ID Type / Status
Subject Tron E177092 entity
Predicate producer P490 FINISHED
Object Donald Kushner E241131 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: Donald Kushner | Statement: [Tron, producer, Donald Kushner]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donald Kushner
Context triple: [Tron, producer, Donald Kushner]
  • A. Donald Kushner chosen
    Donald Kushner is an American film producer best known for producing the groundbreaking science-fiction film "Tron" (1982).
  • B. Theodore James Kushner
    Theodore James Kushner is a son of American investor and former senior White House advisor Jared Kushner and Ivanka Trump, making him a grandchild of former U.S. President Donald Trump.
  • C. Seryl Kushner
    Seryl Kushner is an American businesswoman and matriarch of the Kushner family, best known as the mother of real estate investor and former presidential advisor Jared Kushner.
  • D. Don Katz
    Don Katz is an American entrepreneur and author best known as the founder of the audiobook and spoken-word entertainment company Audible.
  • E. Paul Wernick
    Paul Wernick is an American screenwriter best known for co-writing the hit Deadpool films and other major Hollywood action-comedies.
  • 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_69c69f2583808190bd1a4936c42a5815 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f57b5b4c8190ab839e6a98ee86ed completed March 27, 2026, 9:24 p.m.
NED1 Entity disambiguation (via context triple) batch_69c83c819f00819087fef27e4f4fdc1c completed March 28, 2026, 8:39 p.m.
Created at: March 27, 2026, 3:43 p.m.