Triple

T15698491
Position Surface form Disambiguated ID Type / Status
Subject Frances (1982 film) E380530 entity
Predicate screenwriter P2831 FINISHED
Object Nicholas Kazan E502205 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: Nicholas Kazan | Statement: [Frances (1982 film), screenwriter, Nicholas Kazan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nicholas Kazan
Context triple: [Frances (1982 film), screenwriter, Nicholas Kazan]
  • A. Nicholas Kazan chosen
    Nicholas Kazan is an American screenwriter, playwright, and director known for films such as "Reversal of Fortune" and for being the son of famed director Elia Kazan.
  • B. Robert Kazinsky
    Robert Kazinsky is a British actor best known for his roles in the TV series "EastEnders" and "True Blood," as well as in films such as "Pacific Rim" and "Warcraft."
  • C. Michael K. Powell
    Michael K. Powell is an American lawyer and politician best known for serving as chairman of the Federal Communications Commission (FCC) from 2001 to 2005.
  • D. Jonathan Kempner
    Jonathan Kempner is an American lawyer and nonprofit executive best known for leading major housing and real estate industry organizations.
  • E. David Cromer
    David Cromer is an American director and actor known for his acclaimed work in theater, including innovative stage productions and performances on and off Broadway.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f6c3328819081325b702ca92862 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff7571f1888190b83af75ec9c7432b completed May 9, 2026, 5:57 p.m.
Created at: April 10, 2026, 4:44 a.m.