Triple

T22810646
Position Surface form Disambiguated ID Type / Status
Subject Donna Who E564662 entity
Predicate name P16 FINISHED
Object Donna Who 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: Donna Who | Statement: [Donna Who, name, Donna Who]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Donna Who
Context triple: [Donna Who, name, Donna Who]
  • A. Donna Who chosen
    Donna Who is a resident of Whoville and the caring single mother of Cindy-Lou Who in the 2018 animated film "The Grinch."
  • B. Melody Pond
    Melody Pond is the time-traveling daughter of Amy Pond and Rory Williams who later becomes the enigmatic River Song in the Doctor Who universe.
  • C. Donna
    Donna is a feminine given name of Italian origin that has been widely used in English-speaking countries.
  • D. Sandra Shaw
    Sandra Shaw was the screen name of American actress Veronica Balfe, who appeared in several films of the 1930s and was married to actor Gary Cooper.
  • E. Juno MacGuff
    Juno MacGuff is the witty, independent, and unexpectedly pregnant teenage protagonist of the 2007 film "Juno," known for her sharp dialogue and emotional maturity.
  • 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_69e245823f4c8190ade442cdcc2c224a completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17d60186881908f6cb609c536dc91 completed April 29, 2026, 3:39 a.m.
Created at: April 17, 2026, 3:32 p.m.