Triple

T10500180
Position Surface form Disambiguated ID Type / Status
Subject Al Green E247651 entity
Predicate name P16 FINISHED
Object Al Green E111448 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: Al Green | Statement: [Al Green, name, Al Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Al Green
Context triple: [Al Green, name, Al Green]
  • A. Al Green chosen
    Al Green is an American soul and R&B singer renowned for his smooth, emotive vocals and classic hits like "Let's Stay Together," which made him a defining figure of 1970s soul music.
  • B. Al Green
    Al Green is an American Democratic politician and longtime member of the U.S. House of Representatives known for representing a Houston-area district and for his advocacy on civil rights and social justice issues.
  • C. Luther Vandross
    Luther Vandross was an American R&B and soul singer, songwriter, and producer renowned for his smooth, emotive vocals and classic love ballads.
  • D. Donny Hathaway
    Donny Hathaway was an influential American soul singer, pianist, and songwriter known for his rich, emotive vocals and classic recordings in the 1970s.
  • E. Bill Withers
    Bill Withers was an American singer-songwriter and musician best known for soulful hits like "Ain't No Sunshine," "Lean on Me," and "Lovely Day."
  • 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_69d381c309b88190af78aa681cf6a4c2 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d5098ef57c8190a9803c2c1736d299 completed April 7, 2026, 1:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d94b0d05a88190be036a6e4ab374a7 completed April 10, 2026, 7:10 p.m.
Created at: April 6, 2026, 12:25 p.m.