Triple

T4101099
Position Surface form Disambiguated ID Type / Status
Subject Mudbound E87941 entity
Predicate starring P1507 FINISHED
Object Jason Clarke E15309 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 Clarke | Statement: [Mudbound, starring, Jason Clarke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jason Clarke
Context triple: [Mudbound, starring, Jason Clarke]
  • A. Jason Clarke chosen
    Jason Clarke is an Australian actor known for his intense performances in films such as "Zero Dark Thirty," "Dawn of the Planet of the Apes," and "Chappaquiddick."
  • B. Ben Foster
    Ben Foster is an American actor known for his intense, often gritty performances in films such as "3:10 to Yuma," "Hell or High Water," and "The Messenger."
  • C. Frank Grillo
    Frank Grillo is an American actor best known for his tough, action-oriented roles in films such as the Purge series and the Marvel Cinematic Universe.
  • D. Jeremy Renner
    Jeremy Renner is an American actor and musician best known for his roles in films such as "The Hurt Locker" and as Hawkeye in the Marvel Cinematic Universe.
  • E. Michael Shannon
    Michael Shannon is an American actor known for his intense, often villainous roles in films such as "Revolutionary Road," "Take Shelter," and "The Shape of Water," as well as his acclaimed work in television and theater.
  • 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_69aed94564cc8190a9c1457daedb6e7f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefd0ed168819093c83ba079d6725c completed March 9, 2026, 5:02 p.m.
NED1 Entity disambiguation (via context triple) batch_69b57f1d1ab081909b7999e8feede458 completed March 14, 2026, 3:30 p.m.
Created at: March 9, 2026, 3:40 p.m.