Triple

T13994822
Position Surface form Disambiguated ID Type / Status
Subject Down E336666 entity
Predicate writer P1360 FINISHED
Object Jared Cotter E922280 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: Jared Cotter | Statement: [Down, writer, Jared Cotter]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jared Cotter
Context triple: [Down, writer, Jared Cotter]
  • A. Jared Cotter chosen
    Jared Cotter is an American singer, songwriter, and television host who gained national attention as a contestant on the sixth season of American Idol.
  • B. Todd Keller
    Todd Keller is a musician best known for his past role as a member of the American psychedelic rock band The Black Angels.
  • C. Matt Mattox
    Matt Mattox was an American jazz and musical theatre dancer and choreographer, best known for his athletic, angular style and influential work in mid-20th-century stage and film musicals.
  • D. Ryan Yarbrough
    Ryan Yarbrough is an American professional baseball pitcher known for his tenure with the Tampa Bay Rays in Major League Baseball.
  • E. Chad Feldheimer
    Chad Feldheimer is a dim-witted but enthusiastic gym employee whose discovery of what he believes to be sensitive government information drives much of the darkly comic chaos in the film "Burn After Reading."
  • 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_69d81c645c5c8190b1fd16a285a1b78a completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2eb53f508190855cd69b8061dd77 completed April 14, 2026, 12:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbac9a7e8c8190a0fd0cd67ff50741 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.