Triple

T13394209
Position Surface form Disambiguated ID Type / Status
Subject Joseph MacDonald E319655 entity
Predicate notableWork P4 FINISHED
Object Pinky E82384 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: Pinky | Statement: [Joseph MacDonald, notableWork, Pinky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pinky
Context triple: [Joseph MacDonald, notableWork, Pinky]
  • A. Pinky chosen
    Pinky is a 1949 American drama film directed by Elia Kazan that explores race, identity, and passing in the segregated American South.
  • B. Pinky
    Pinky is a comedic character appearing in the Marx Brothers film "Horse Feathers."
  • C. Pookie
    Pookie is a tragic, crack-addicted informant character from the 1991 crime film "New Jack City," portrayed by Chris Rock.
  • D. Pinky Rose
    Pinky Rose is the shy, emotionally fragile young woman played by Sissy Spacek in Robert Altman’s 1977 psychological drama film "3 Women."
  • E. Penny Wheep
    Penny Wheep is a poetry collection by Scottish modernist writer Hugh MacDiarmid that reflects his innovative use of Scots language and exploration of national and social themes.
  • 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_69d806b943cc8190b6af624d385d7e12 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69dba0d892d08190b1b192b93fe3d72d completed April 12, 2026, 1:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69f73981816881908aac3ab6b1921904 completed May 3, 2026, 12:03 p.m.
Created at: April 9, 2026, 9:34 p.m.