Triple

T10325687
Position Surface form Disambiguated ID Type / Status
Subject The Old Guard E242754 entity
Predicate cinematographyBy P1953 FINISHED
Object Tami Reiker E589938 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: Tami Reiker | Statement: [The Old Guard, cinematographyBy, Tami Reiker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tami Reiker
Context triple: [The Old Guard, cinematographyBy, Tami Reiker]
  • A. Tami Reiker chosen
    Tami Reiker is an American cinematographer known for her visually striking work on films and television, including the acclaimed drama "One Night in Miami..." and the series "Carnivàle."
  • B. Tami Taylor
    Tami Taylor is a compassionate high school guidance counselor and the strong, morally grounded wife of coach Eric Taylor in the television series "Friday Night Lights."
  • C. Tracy Reiner
    Tracy Reiner is an American actress known for her roles in films such as "A League of Their Own" and "When Harry Met Sally...."
  • D. Laura Rister
    Laura Rister is a film producer and executive known for her work on independent and prestige projects, including the financial thriller "Margin Call."
  • E. Andrea Kremer
    Andrea Kremer is an American sports journalist and broadcaster renowned for her pioneering NFL coverage and in-depth reporting on major sporting events.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d7cd76348190b93562112300acfc completed April 7, 2026, 10:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d94aec37288190bd9060ba39ec4df2 completed April 10, 2026, 7:09 p.m.
Created at: April 6, 2026, 11:51 a.m.