Triple

T2919291
Position Surface form Disambiguated ID Type / Status
Subject Tootsie E78679 entity
Predicate starring P1507 FINISHED
Object Dustin Hoffman E123769 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: Dustin Hoffman | Statement: [Tootsie, starring, Dustin Hoffman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dustin Hoffman
Context triple: [Tootsie, starring, Dustin Hoffman]
  • A. Dustin Hoffman chosen
    Dustin Hoffman is an acclaimed American actor renowned for his versatile, character-driven performances in films such as "The Graduate," "Midnight Cowboy," and "Rain Man."
  • B. Ned Beatty
    Ned Beatty was an acclaimed American character actor known for his powerful supporting roles in films such as "Deliverance," "Network," and "Superman."
  • C. Elliott Gould
    Elliott Gould is an American actor known for his roles in films such as "M*A*S*H," "Bob & Carol & Ted & Alice," and the "Ocean's Eleven" series.
  • D. Roy Scheider
    Roy Scheider was an American actor best known for his intense, everyman performances in films such as "The French Connection," "All That Jazz," and "Jaws."
  • E. William Hurt
    William Hurt was an acclaimed American actor known for his intense, introspective performances in films such as "Kiss of the Spider Woman," "Broadcast News," and "The Big Chill."
  • 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_69ad8b0c2ad081909ff87050ae542bb9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad96a53f8c8190b188d549f1161e84 completed March 8, 2026, 3:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e181898819087ed4acfd24c00a1 completed March 11, 2026, 8:55 a.m.
Created at: March 8, 2026, 2:54 p.m.