Triple

T22754487
Position Surface form Disambiguated ID Type / Status
Subject Simone Johnson E562800 entity
Predicate father P120 FINISHED
Object Dwayne Johnson 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: Dwayne Johnson | Statement: [Simone Johnson, father, Dwayne Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dwayne Johnson
Context triple: [Simone Johnson, father, Dwayne Johnson]
  • A. Dwayne Johnson chosen
    Dwayne Johnson is an American actor, film producer, and former professional wrestler widely known by his ring name "The Rock" and for starring in numerous blockbuster action and adventure films.
  • B. Terry Crews
    Terry Crews is an American actor, former NFL player, and television host known for his comedic roles, muscular physique, and energetic personality.
  • C. Channing Tatum
    Channing Tatum is an American actor and producer known for his roles in films such as "Magic Mike," "21 Jump Street," and various action and comedy movies.
  • D. John Cena
    John Cena is an American professional wrestler, actor, and television host best known as one of WWE’s most popular and decorated superstars.
  • E. Scott Adkins
    Scott Adkins is an English actor and highly skilled martial artist best known for his roles in action films such as the Undisputed series and numerous high-intensity fight-driven movies.
  • 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_69e24551ec7881909a9c924dbea155f6 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f179bc48788190b3deb9287d02cb2c completed April 29, 2026, 3:23 a.m.
Created at: April 17, 2026, 3:25 p.m.