Triple

T20164084
Position Surface form Disambiguated ID Type / Status
Subject Cosmo E491784 entity
Predicate child P120 FINISHED
Object Poof 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: Poof | Statement: [Cosmo, child, Poof]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Poof
Context triple: [Cosmo, child, Poof]
  • A. Poof chosen
    Poof is the baby fairy godchild of Cosmo and Wanda in the animated series "The Fairly OddParents," known for his powerful magic and infant mischief.
  • B. Puff
    Puff is the central character of the story "Human Nature," around whom the narrative’s themes and events primarily revolve.
  • C. Pofi
    Pofi is a small Italian town in the Lazio region, known for its volcanic landscape and archaeological finds dating back to prehistoric times.
  • D. The Poof Point
    The Poof Point is a 2001 Disney Channel Original Movie that blends science fiction and family comedy as two teens race to stop their scientist parents from regressing into children after a time-travel experiment goes wrong.
  • E. Pooc
    Pooc is a dialect of the Paicî language, an Austronesian language spoken in New Caledonia.
  • 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_69da6266c6888190bc1a3ecf24814d34 completed April 11, 2026, 3:01 p.m.
NER Named-entity recognition batch_69e6684376408190a68890ab48fa5424 completed April 20, 2026, 5:54 p.m.
Created at: April 11, 2026, 11:35 p.m.