Triple

T17903732
Position Surface form Disambiguated ID Type / Status
Subject Ellie Williams E447646 entity
Predicate motionCaptureActor P83328 FINISHED
Object Ashley 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: Ashley Johnson | Statement: [Ellie Williams, motionCaptureActor, Ashley Johnson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ashley Johnson
Context triple: [Ellie Williams, motionCaptureActor, Ashley Johnson]
  • A. Ashley Johnson chosen
    Ashley Johnson is an American actress and voice actress known for her roles in television, film, and video games, including voicing Ellie in "The Last of Us" series.
  • B. Celeste Van Dien
    Celeste Van Dien is the daughter of American actress Catherine Oxenberg and actor Casper Van Dien.
  • C. Emily Alyn Lind
    Emily Alyn Lind is an American actress known for her roles in film and television, including playing the young Amanda Clarke on the TV series "Revenge."
  • D. Anna Torv
    Anna Torv is an Australian actress best known for her lead role as FBI agent Olivia Dunham in the science fiction television series "Fringe."
  • E. Elisha Cuthbert
    Elisha Cuthbert is a Canadian actress known for her roles in film and television, including prominent parts in series like "24" and various comedy and thriller 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_69d8b9f6d394819082a6d69fd1e23d2f completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49e9a9cfc8190879fc36dfdeb562b completed April 19, 2026, 9:21 a.m.
Created at: April 10, 2026, 10:19 a.m.