Triple

T9830261
Position Surface form Disambiguated ID Type / Status
Subject Detroit (2017 film) E238763 entity
Predicate starring P1507 FINISHED
Object Jason Mitchell E233166 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: Jason Mitchell | Statement: [Detroit (2017 film), starring, Jason Mitchell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jason Mitchell
Context triple: [Detroit (2017 film), starring, Jason Mitchell]
  • A. Jason Mitchell chosen
    Jason Mitchell is an American actor known for his breakout role as Eazy-E in "Straight Outta Compton" and appearances in films such as "Mudbound" and "Kong: Skull Island."
  • B. Michael Ealy
    Michael Ealy is an American actor known for his roles in films like "Barbershop," "Think Like a Man," and "2 Fast 2 Furious," as well as various television series.
  • C. Jeffery Wood
    Jeffery Wood is an American actor best known for his role on the television sitcom "In the House."
  • D. Eriq La Salle
    Eriq La Salle is an American actor, director, and producer best known for his role as Dr. Peter Benton on the television series "ER."
  • E. Leo Willis
    Leo Willis was an American character actor active during the silent and early sound film eras, often appearing in comedies alongside stars like Harold Lloyd.
  • 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_69ca84e0dd1881909800765d1e21f735 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb3297bd88190bf8c53a4ba00e0ae completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5bc17c08190ad094def4fbf9921 completed April 5, 2026, 3:23 a.m.
Created at: March 30, 2026, 8:32 p.m.