Triple

T1823690
Position Surface form Disambiguated ID Type / Status
Subject Lights of New York E40601 entity
Predicate starring P1507 FINISHED
Object Tom Dugan E48184 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: Tom Dugan | Statement: [Lights of New York, starring, Tom Dugan]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tom Dugan
Context triple: [Lights of New York, starring, Tom Dugan]
  • A. Tom Dugan chosen
    Tom Dugan was an American character actor of the early 20th century, known for his numerous supporting roles in Hollywood films.
  • B. Arthur Gettleman
    Arthur Gettleman was the husband of American actress Estelle Getty, best known for her role as Sophia Petrillo on the television series "The Golden Girls."
  • C. George Walsh
    George Walsh was an American silent film actor and the younger brother of renowned director Raoul Walsh.
  • D. Joseph Gargan
    Joseph Gargan was an American lawyer and political operative, a cousin and close associate of Senator Ted Kennedy who became known for his involvement in and later criticism of Kennedy’s actions surrounding the Chappaquiddick incident.
  • E. Bill Bryant
    Bill Bryant is an American businessman and Republican politician from Washington state who has served as a Port of Seattle commissioner and ran for governor in 2016.
  • 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_69a8864644bc8190b2358ab897194ac1 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa662d13e88190a22b0faf0d848c7d completed March 6, 2026, 5:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69addf42de6081908182cd3bda9c69e9 completed March 8, 2026, 8:42 p.m.
Created at: March 4, 2026, 7:32 p.m.