Triple

T20389915
Position Surface form Disambiguated ID Type / Status
Subject Mystery Train E498057 entity
Predicate directorOfPhotography P1953 FINISHED
Object Robbie Müller 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: Robbie Müller | Statement: [Mystery Train, directorOfPhotography, Robbie Müller]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robbie Müller
Context triple: [Mystery Train, directorOfPhotography, Robbie Müller]
  • A. Robbie Müller chosen
    Robbie Müller was a renowned Dutch cinematographer celebrated for his innovative, naturalistic visual style in influential art-house and independent films.
  • B. Michael Roskam
    Michael Roskam is a Belgian film director, screenwriter, and producer best known for his crime drama "Bullhead" and his work in both European and American cinema.
  • C. Derek Dreyer
    Derek Dreyer is a prominent computer scientist known for his work in programming languages, type theory, and formal verification.
  • D. Markus Majowski
    Markus Majowski is a German actor and comedian known for his roles in film, television, and theater.
  • E. Andrew Dost
    Andrew Dost is an American musician and multi-instrumentalist best known as the pianist and a founding member of the indie pop band Fun.
  • 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_69e0b4a71ebc8190b153a36c738730f4 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6790e65a081909832855758fffd14 completed April 20, 2026, 7:05 p.m.
Created at: April 16, 2026, 11:28 a.m.