Triple

T9788809
Position Surface form Disambiguated ID Type / Status
Subject Inside Out 2 E237554 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: [Inside Out 2, storyBy, Kelsey Mann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kelsey Mann
Context triple: [Inside Out 2, 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. 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.
  • C. 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.
  • D. Mallory Hanson
    Mallory Hanson is a central supporting character in the comedy series "Grace and Frankie," known as one of Grace's daughters who often juggles family responsibilities and personal ambitions.
  • E. Kelsey Burrell
    Kelsey Burrell is known as the child of the Jamaican-American reggae fusion singer and rapper Shaggy.
  • 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_69ca84da927881909bda80caecad6010 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cda2131164819099e8644e40a3cab6 completed April 1, 2026, 10:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1e40ba788819084c3c01518a72e4e completed April 5, 2026, 4:24 a.m.
Created at: March 30, 2026, 8:27 p.m.