Triple

T22167875
Position Surface form Disambiguated ID Type / Status
Subject The Kiss (1896 film) E547842 entity
Predicate stars P1956 FINISHED
Object May Irwin NE NERFINISHED

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: May Irwin | Statement: [The Kiss (1896 film), stars, May Irwin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: May Irwin
Context triple: [The Kiss (1896 film), stars, May Irwin]
  • A. May Irwin chosen
    May Irwin was a popular Canadian-American stage and vaudeville actress and singer of the late 19th and early 20th centuries, known for her comedic roles and early appearance in silent film.
  • B. Nancy O’Dell
    Nancy O’Dell is an American television host and entertainment journalist best known for her long-running work on major entertainment news programs.
  • C. Mary Ellen Irwin
    Mary Ellen Irwin is best known as the wife of Apollo 15 astronaut James B. Irwin.
  • D. Sheri Bylander
    Sheri Bylander is a film editor best known for her work on the Disney Channel original movie "Halloweentown II: Kalabar's Revenge."
  • E. Nancy Watson
    Nancy Watson is known primarily as the daughter of influential American folk and bluegrass guitarist Doc Watson.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e3c4c5c81908d336165816b12e0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12a6642b08190980fa0c0d2bb4229 completed April 28, 2026, 9:45 p.m.
Created at: April 16, 2026, 8:34 p.m.