Triple

T18067844
Position Surface form Disambiguated ID Type / Status
Subject Randy Goodrum E432335 entity
Predicate hasWrittenSongsFor P44022 FINISHED
Object Peabo Bryson 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: Peabo Bryson | Statement: [Randy Goodrum, hasWrittenSongsFor, Peabo Bryson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Peabo Bryson
Context triple: [Randy Goodrum, hasWrittenSongsFor, Peabo Bryson]
  • A. Peabo Bryson chosen
    Peabo Bryson is an American R&B and soul singer best known for his powerful ballads and duets, including several hit Disney movie theme songs.
  • B. Michael McDonald
    Michael McDonald is an American singer, songwriter, and keyboardist known for his soulful baritone voice and work with the Doobie Brothers as well as a successful solo career.
  • C. Michael McDonald
    Michael McDonald is an American actor and comedian best known for his long-running work and memorable characters on the sketch comedy series MADtv.
  • D. Philip Bailey
    Philip Bailey is an American R&B, soul, and gospel singer best known as a lead vocalist of Earth, Wind & Fire, renowned for his distinctive falsetto voice.
  • E. Ray Conniff
    Ray Conniff was an American bandleader, arranger, and trombonist best known for his easy-listening orchestral and choral recordings that gained wide popularity in the mid-20th century.
  • 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_69d8b9070cac81909fa9473fb1c3f1c7 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4cceb020081909329492591e7b1f2 completed April 19, 2026, 12:39 p.m.
Created at: April 10, 2026, 10:26 a.m.