Triple

T16750913
Position Surface form Disambiguated ID Type / Status
Subject Olivia Cooke E407073 entity
Predicate notableWork P4 FINISHED
Object Sound of Metal E779085 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: Sound of Metal | Statement: [Olivia Cooke, notableWork, Sound of Metal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sound of Metal
Context triple: [Olivia Cooke, notableWork, Sound of Metal]
  • A. Sound of Metal chosen
    Sound of Metal is a 2019 drama film about a heavy metal drummer whose life is upended when he begins to lose his hearing, exploring themes of identity, addiction, and the Deaf community.
  • B. Dead Sound
    Dead Sound is a musical act known for its work with musician Bill Schneider.
  • C. The Sound Inside
    The Sound Inside is a critically acclaimed stage play by Adam Rapp that explores the intense, unsettling relationship between a Yale creative writing professor and one of her students.
  • D. The Sound
    "The Sound" is a catchy, synth-driven pop song by English band The 1975, known for its infectious chorus and polished, danceable production.
  • E. The Sound
    The Sound is the strait between Denmark and Sweden that connects the Baltic Sea to the Kattegat and is one of the world's busiest waterways.
  • 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_69d8838ffb088190a0b11149929006bf completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3aa271de48190b4a535408aeef734 completed April 18, 2026, 3:58 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a522255c8190ab16d7ad233fcd3b completed May 10, 2026, 3:32 p.m.
Created at: April 10, 2026, 5:21 a.m.