Triple

T1227559
Position Surface form Disambiguated ID Type / Status
Subject Cinderella Man E26359 entity
Predicate starring P1507 FINISHED
Object Craig Bierko E71819 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: Craig Bierko | Statement: [Cinderella Man, starring, Craig Bierko]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig Bierko
Context triple: [Cinderella Man, starring, Craig Bierko]
  • A. Craig Bierko chosen
    Craig Bierko is an American actor known for his work in film, television, and theater, often playing charismatic or villainous roles.
  • B. Jim Loscutoff
    Jim Loscutoff was an American professional basketball forward best known for his rugged defense and seven NBA championships with the Boston Celtics in the 1950s and 1960s.
  • C. Jesse Michaels
    Jesse Michaels is an American musician and artist best known as the lead vocalist and lyricist of the influential ska punk band Operation Ivy.
  • D. Matt Messina
    Matt Messina is an American film and television composer best known for his award-winning score for the movie "Juno."
  • E. Keith Fraase
    Keith Fraase is a film editor best known for his work on the movie "Chappaquiddick."
  • 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_69a49484688c8190a1bf285eb396a8b6 completed March 1, 2026, 7:33 p.m.
NER Named-entity recognition batch_69a4be3b32a08190a36e96a3e51976eb completed March 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69aca2eb158081909f1175d8f4daaa96 completed March 7, 2026, 10:12 p.m.
Created at: March 1, 2026, 7:47 p.m.