Triple

T21552574
Position Surface form Disambiguated ID Type / Status
Subject One Sweet Day E531801 entity
Predicate writer P1360 FINISHED
Object Nathan Morris 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: Nathan Morris | Statement: [One Sweet Day, writer, Nathan Morris]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nathan Morris
Context triple: [One Sweet Day, writer, Nathan Morris]
  • A. Nathan Morris chosen
    Nathan Morris is an American R&B singer and founding member of the vocal group Boyz II Men.
  • B. Gerald Levert
    Gerald Levert was an American R&B singer, songwriter, and producer known for his soulful vocals, solo hits, and work with the group LeVert.
  • C. Otis Wilbury
    Otis Wilbury is the pseudonymous persona used by musician Jeff Lynne as a member of the supergroup Traveling Wilburys.
  • D. Johnny Gill
    Johnny Gill is an American R&B singer known both for his solo career and for joining the legendary boy band New Edition in the late 1980s.
  • E. Morris Day
    Morris Day is an American singer, songwriter, and bandleader best known as the charismatic frontman of The Time and a frequent collaborator in the Minneapolis funk scene.
  • 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_69e0c460232c81908de2c3819d17c00e completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eeb59375f481909d9e2b66d18c7c32 completed April 27, 2026, 1:02 a.m.
Created at: April 16, 2026, 6:29 p.m.