Triple

T22453322
Position Surface form Disambiguated ID Type / Status
Subject Leviathan E555047 entity
Predicate producer P490 FINISHED
Object Matt Bayles NE NERFINISHED

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: Matt Bayles | Statement: [Leviathan, producer, Matt Bayles]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Matt Bayles
Context triple: [Leviathan, producer, Matt Bayles]
  • A. Matt Bayles chosen
    Matt Bayles is an American record producer and audio engineer known for his work with influential rock and metal bands such as Mastodon, Isis, and Minus the Bear.
  • B. Scott Bailes
    Scott Bailes is a former Major League Baseball pitcher who played primarily for the Cleveland Indians during the late 1980s and early 1990s.
  • C. Mark Batey
    Mark Batey is a notable individual recognized for his contributions in his professional field, likely in academia or industry.
  • D. Matt Baird
    Matt Baird is a technology entrepreneur best known as a founder of the software company Embarcadero Technologies.
  • E. Alex T. Farnsley
    Alex T. Farnsley was an American whiskey executive and entrepreneur best known as one of the founders of the influential Stitzel-Weller bourbon distillery in Kentucky.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e5113208190ab58c6b595f9d1d0 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15b4d6368819082cafbbd83339fbf completed April 29, 2026, 1:13 a.m.
Created at: April 16, 2026, 8:48 p.m.