Triple

T17186417
Position Surface form Disambiguated ID Type / Status
Subject Hey What E417119 entity
Predicate producer P490 FINISHED
Object BJ Burton E329877 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: BJ Burton | Statement: [Hey What, producer, BJ Burton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: BJ Burton
Context triple: [Hey What, producer, BJ Burton]
  • A. BJ Burton chosen
    BJ Burton is an American record producer and engineer known for his experimental, genre-blending work with artists such as Bon Iver and Low.
  • B. Matt Tifft
    Matt Tifft is an American professional stock car racing driver who has competed in NASCAR’s top national series, including the Cup Series.
  • C. William D. Byron
    William D. Byron was a U.S. Congressman from Maryland who served briefly in the early 1940s before dying in a plane crash while in office.
  • D. Adam Burton
    Adam Burton is a fictional character from the romantic comedy film "Little Manhattan," which follows a young boy's first experience with love in New York City.
  • E. Jarrod Dillon
    Jarrod Dillon is a sports executive who serves as the president of Major League Soccer club Orlando City SC.
  • 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_69d886d5f34c8190b24564dfaa63f3fb completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42d962b988190bdbba81ac63c7e6e completed April 19, 2026, 1:19 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0170e784bc8190a052c4fe87be124a completed May 11, 2026, 6:02 a.m.
Created at: April 10, 2026, 5:37 a.m.