Triple

T21722288
Position Surface form Disambiguated ID Type / Status
Subject Down to Earth E536188 entity
Predicate hasPart P35 FINISHED
Object All Night Long — 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: All Night Long | Statement: [Down to Earth, hasPart, All Night Long]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: All Night Long
Context triple: [Down to Earth, hasPart, All Night Long]
  • A. All Night Long chosen
    All Night Long is a 1962 British jazz-infused drama film directed by Basil Dearden that reimagines Shakespeare’s Othello in London’s nightclub scene.
  • B. All Night Long
    "All Night Long" is a dance-pop song by British singer Alexandra Burke, known for its upbeat production and club-friendly sound.
  • C. All Night Long
    "All Night Long" is a 1956 hard bop jazz album led by guitarist Kenny Burrell, celebrated for its extended improvisations and classic Prestige Records session lineup.
  • D. All Night Long
    "All Night Long" is a song featured on the R&B album *U Turn* by Brian McKnight.
  • E. All Night Long
    "All Night Long" is a hard rock song best known as a hit single performed by vocalist Graham Bonnet during his tenure with Ritchie Blackmore's band Rainbow.
  • 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_69e0c46c6dd88190a595375fa6ebd701 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69efd97032c08190820b87a288e77293 completed April 27, 2026, 9:47 p.m.
Created at: April 16, 2026, 6:47 p.m.