Triple

T16252020
Position Surface form Disambiguated ID Type / Status
Subject King of New York E394530 entity
Predicate producer P490 FINISHED
Object Mary Kane E394530 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: Mary Kane | Statement: [King of New York, producer, Mary Kane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Kane
Context triple: [King of New York, producer, Mary Kane]
  • A. Mary Kane
    Mary Kane is a pivotal supporting character in the film "Citizen Kane," known as Charles Foster Kane’s mother whose early decision about his upbringing profoundly shapes his life.
  • B. Mary Kane chosen
    Mary Kane is a film producer known for her work on the 1990 crime drama "King of New York."
  • C. Mollie MacArthur
    Mollie MacArthur is known primarily as the mother of Irish murderer Malcolm MacArthur, who was at the center of a notorious 1982 double killing that shocked Ireland.
  • D. Mollie Currie
    Mollie Currie is a person notable enough to be recognized as a bearer of the Currie surname, though specific widely known biographical details about her are not readily available.
  • E. Caroline O'Neill
    Caroline O'Neill is a British actress known for her work in television dramas, including a role in the series "The Lakes."
  • 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_69d87f2171208190951025e526947816 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e24597b74481908fdb8175628a57a1 completed April 17, 2026, 2:37 p.m.
NED1 Entity disambiguation (via context triple) batch_6a000ee788f88190b16d267f1eee6d62 completed May 10, 2026, 4:51 a.m.
Created at: April 10, 2026, 5:04 a.m.