Triple

T14153101
Position Surface form Disambiguated ID Type / Status
Subject Tony Bancroft E350735 entity
Predicate coDirectorWith P17194 FINISHED
Object Barry Cook E343850 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: Barry Cook | Statement: [Tony Bancroft, coDirectorWith, Barry Cook]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Barry Cook
Context triple: [Tony Bancroft, coDirectorWith, Barry Cook]
  • A. Barry Cook chosen
    Barry Cook is an American film director and animator best known for co-directing Disney's animated feature "Mulan" (1998).
  • B. Jon Cooksey
    Jon Cooksey is a television and film writer best known for co-writing the popular Disney Channel movie "Halloweentown."
  • C. Barry Miller
    Barry Miller is an American actor best known for his roles in films like "Saturday Night Fever" and "Fame," as well as various television and stage productions.
  • D. Jon Barry
    Jon Barry is a former American professional basketball player and current NBA television analyst.
  • E. Donald Cooksey
    Donald Cooksey was an American physicist known for his work in nuclear physics and his leadership role at the MIT Radiation Laboratory during World War II.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de6133754881908e1e97db71772deb completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd2802ba608190849313ff2661cd07 completed May 8, 2026, 12:02 a.m.
Created at: April 10, 2026, 12:57 a.m.