Triple

T15625135
Position Surface form Disambiguated ID Type / Status
Subject The Good Dinosaur E375658 entity
Predicate storyBy P1955 FINISHED
Object Kelsey Mann E824598 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: Kelsey Mann | Statement: [The Good Dinosaur, storyBy, Kelsey Mann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelsey Mann
Context triple: [The Good Dinosaur, storyBy, Kelsey Mann]
  • A. Kelsey Mann chosen
    Kelsey Mann is an American film director and storyboard artist at Pixar, best known for directing the animated feature "Inside Out 2."
  • B. Kelsey Peters
    Kelsey Peters is a driven and ambitious young publishing executive and one of the central protagonists on the television series "Younger."
  • C. Kelsey Hooper
    Kelsey Hooper is a central child protagonist in the Doctor Who spin-off special "Invasion of the Bane," where she becomes closely involved with Sarah Jane Smith in uncovering an alien conspiracy.
  • D. Kaylee Hottle
    Kaylee Hottle is a young American actress best known for her breakout role in the MonsterVerse film franchise, where she portrays Jia, a deaf orphan who communicates with King Kong.
  • E. Kelsey Asbille
    Kelsey Asbille is an American actress known for her roles in television series such as Yellowstone and Teen Wolf, as well as films like Wind River.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e9e5e248190ae54cda1fde51efb completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffeb7c2a6081908e957d39ec056062 completed May 10, 2026, 2:20 a.m.
Created at: April 10, 2026, 4:14 a.m.