Triple

T22195857
Position Surface form Disambiguated ID Type / Status
Subject Rufus Norris E548547 entity
Predicate notableWork P4 FINISHED
Object Broken 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: Broken | Statement: [Rufus Norris, notableWork, Broken]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Broken
Context triple: [Rufus Norris, notableWork, Broken]
  • A. Broken chosen
    "Broken" is a British television drama series starring Sean Bean as a troubled Catholic priest grappling with faith, morality, and the struggles of his working-class parishioners.
  • B. Broken
    "Broken" is a hauntingly melodic indie-folk song by Canadian singer-songwriter Patrick Watson, known for its ethereal vocals and cinematic, atmospheric arrangement.
  • C. Broken
    "Broken" is a song featured on the Norah Jones album "Not Too Late."
  • D. Broken
    "Broken" is a song by Canadian rock band The Guess Who, known for its emotive lyrics and classic rock sound.
  • E. Broken
    "Broken" is likely a track from the album *The Process of Belief* by punk rock band Bad Religion.
  • 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_69e11e3ecc7c8190b5f94cd8f42e9d37 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f12ae6f7a881908cf1772326f91467 completed April 28, 2026, 9:47 p.m.
Created at: April 16, 2026, 8:35 p.m.