Triple

T12266331
Position Surface form Disambiguated ID Type / Status
Subject Power Up E292355 entity
Predicate featuresMember P17143 FINISHED
Object Brian Johnson E290666 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: Brian Johnson | Statement: [Power Up, featuresMember, Brian Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brian Johnson
Context triple: [Power Up, featuresMember, Brian Johnson]
  • A. Brian Johnson
    Brian Johnson is a film editor known for his work on the documentary "He Named Me Malala."
  • B. Brian Johnson chosen
    Brian Johnson is a British rock singer best known as the longtime lead vocalist of the Australian hard rock band AC/DC.
  • C. Angus Young
    Angus Young is the lead guitarist, co-founder, and schoolboy-uniform-clad stage icon of the Australian rock band AC/DC.
  • D. Michael Hutchence
    Michael Hutchence was the charismatic lead singer and frontman of the Australian rock band INXS, known for his distinctive voice, magnetic stage presence, and influential role in 1980s and 1990s rock music.
  • E. Cliff Williams
    Cliff Williams is an English musician best known as the longtime bassist and backing vocalist for the Australian rock band AC/DC.
  • 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_69d6ab6856488190b5d31178d5015f8e completed April 8, 2026, 7:24 p.m.
NER Named-entity recognition batch_69d91cdc42988190b4e2a6591a6f919d completed April 10, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5b3ced0819083382a0aceda171a completed May 3, 2026, 7:13 a.m.
Created at: April 8, 2026, 9:52 p.m.