Triple

T1787579
Position Surface form Disambiguated ID Type / Status
Subject Elton John E39424 entity
Predicate collaboratedWith P435 FINISHED
Object George Michael E98964 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: George Michael | Statement: [Elton John, collaboratedWith, George Michael]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: George Michael
Context triple: [Elton John, collaboratedWith, George Michael]
  • A. George Michael chosen
    George Michael was an English singer, songwriter, and record producer who achieved global fame both as a member of Wham! and as a solo artist, becoming one of the best-selling musicians of all time.
  • B. Robbie Williams
    Robbie Williams is an English pop singer and entertainer who rose to fame with the boy band Take That before achieving massive success as a solo artist.
  • C. Boy George
    Boy George is an English singer, songwriter, and DJ best known as the flamboyant lead vocalist of the 1980s pop band Culture Club.
  • D. Paul Young
    Paul Young is an American politician serving as the mayor of Memphis, Tennessee.
  • E. Cliff Richard
    Cliff Richard is a British pop singer and entertainer whose career has spanned several decades, making him one of the best-selling music artists in UK history.
  • 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_69a88631854081909723959921e45c2b completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa650fd3448190a6a2c979db982cae completed March 6, 2026, 5:24 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada9a66da8819085867355c174adce completed March 8, 2026, 4:53 p.m.
Created at: March 4, 2026, 7:32 p.m.