Triple

T14552916
Position Surface form Disambiguated ID Type / Status
Subject Upside Down E341462 entity
Predicate performer P1363 FINISHED
Object Jack Johnson E68712 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: Jack Johnson | Statement: [Upside Down, performer, Jack Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jack Johnson
Context triple: [Upside Down, performer, Jack Johnson]
  • A. Jack Johnson chosen
    Jack Johnson is an American singer-songwriter and guitarist known for his mellow acoustic sound and surf-inspired folk-rock music.
  • B. Jack Johnson
    Jack Johnson was an Aboriginal Australian activist and organizer involved in early Indigenous civil rights movements, including key protests against colonial injustices.
  • C. Jack Johnson
    Jack Johnson is an American actor best known for his role as Will Robinson in the 1998 science fiction film "Lost in Space."
  • D. Jack Johnson
    Jack Johnson is a witty and often mischievous middle child on the TV sitcom "Black-ish," known for his humorous one-liners and close bond with his twin sister, Diane.
  • E. Jack Johnson
    Jack Johnson was the first African American world heavyweight boxing champion, renowned for his dominance in the early 20th century and his challenge to racial barriers in sports.
  • 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_69d822db9c8481908213ceb39585f792 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb2f00cec8190a7b6482d18b9a216 completed April 14, 2026, 9:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69ff8752207c81908369bce03b56b25e completed May 9, 2026, 7:13 p.m.
Created at: April 10, 2026, 1:23 a.m.