Triple

T11899723
Position Surface form Disambiguated ID Type / Status
Subject Sick Boy E283117 entity
Predicate producer P490 FINISHED
Object Shaun Frank E954295 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: Shaun Frank | Statement: [Sick Boy, producer, Shaun Frank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Shaun Frank
Context triple: [Sick Boy, producer, Shaun Frank]
  • A. Shaun Frank chosen
    Shaun Frank is a Canadian DJ, producer, and songwriter known for his work in electronic dance music and collaborations with prominent artists.
  • B. Shaun Silva
    Shaun Silva is an American music video director known for his extensive work with major country artists and contributions to contemporary country music visuals.
  • C. Shawn Matthews
    Shawn Matthews is a senior executive associated with the financial services firm Cantor Fitzgerald.
  • D. Shane Salerno
    Shane Salerno is an American screenwriter, producer, and director known for his work on major Hollywood films and television projects, including blockbuster franchises and high-profile documentaries.
  • E. Shawn Eichman
    Shawn Eichman is an American political activist best known as a defendant in the landmark U.S. Supreme Court case that struck down federal prohibitions on flag desecration as unconstitutional.
  • 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_69d6ab2a90b08190a4e818821cc93e6d completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8dd16433881909befca9774bdaab4 completed April 10, 2026, 11:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f4586898888190b58e3102d7edf7df completed May 1, 2026, 7:38 a.m.
Created at: April 8, 2026, 9:44 p.m.