Triple

T10527164
Position Surface form Disambiguated ID Type / Status
Subject Patch Adams E248334 entity
Predicate starring P1507 FINISHED
Object Irma P. Hall E654984 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: Irma P. Hall | Statement: [Patch Adams, starring, Irma P. Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Irma P. Hall
Context triple: [Patch Adams, starring, Irma P. Hall]
  • A. Irma P. Hall chosen
    Irma P. Hall is an American actress best known for her warm, commanding portrayals of matriarchal figures in films such as "Soul Food" and "The Ladykillers."
  • B. Nellie W. Carter
    Nellie W. Carter was the mother of American actor and entertainer Mickey Rooney.
  • C. Faye B. Harwell
    Faye B. Harwell is an American landscape architect known for her work on prominent public memorials and historic landscapes in Washington, D.C.
  • D. Juanita Hall
    Juanita Hall was an American actress and singer best known for originating the role of Bloody Mary in the Broadway and film versions of the musical "South Pacific."
  • E. Hazel B. Briggs
    Hazel B. Briggs was a film technology developer known for her role in creating the innovative widescreen Cinerama process.
  • 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_69d381c5c7448190bec34bee7ec72bac completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d509f5ec348190875c8c877e70ba4a completed April 7, 2026, 1:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69dbd966f0f08190a60ca3bcf0e08e98 completed April 12, 2026, 5:41 p.m.
Created at: April 6, 2026, 12:29 p.m.