Triple

T9735563
Position Surface form Disambiguated ID Type / Status
Subject Food, Inc. E236047 entity
Predicate editedBy P1954 FINISHED
Object Kim Roberts E828701 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: Kim Roberts | Statement: [Food, Inc., editedBy, Kim Roberts]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kim Roberts
Context triple: [Food, Inc., editedBy, Kim Roberts]
  • A. Kim Roberts chosen
    Kim Roberts is a film editor known for her work on the documentary "Waiting for Superman."
  • B. Jill Eikenberry
    Jill Eikenberry is an American actress best known for her Emmy-nominated role as attorney Ann Kelsey on the television series "L.A. Law."
  • C. Nancy Allen
    Nancy Allen is an American actress best known for her roles in films such as "Carrie," "Dressed to Kill," and the "RoboCop" series.
  • D. Danielle Kaye
    Danielle Kaye is known as the spouse of British film director and music video creator Tony Kaye.
  • E. Grace Van Patten
    Grace Van Patten is an American actress known for her nuanced performances in independent films and television series, including notable roles in projects like "The Meyerowitz Stories" and "Nine Perfect Strangers."
  • 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_69ca84d313e88190983ee6ffd0ef60d2 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9eee70d48190af5a833d7b33aaa5 completed April 1, 2026, 10:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69d2285b4c8081908aba8a074288ee00 completed April 5, 2026, 9:16 a.m.
Created at: March 30, 2026, 8:22 p.m.