Triple

T17564976
Position Surface form Disambiguated ID Type / Status
Subject The Pagemaster E427786 entity
Predicate stars P1956 FINISHED
Object Frank Welker 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: Frank Welker | Statement: [The Pagemaster, stars, Frank Welker]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Frank Welker
Context triple: [The Pagemaster, stars, Frank Welker]
  • A. Frank Welker chosen
    Frank Welker is a prolific American voice actor renowned for his work in animation and film, including iconic roles in series like "Scooby-Doo" and "Transformers."
  • B. Jim Cummings
    Jim Cummings is a prolific American voice actor best known for voicing iconic animated characters such as Winnie the Pooh, Tigger, and Darkwing Duck.
  • C. Jeff Bennett
    Jeff Bennett is an American voice actor known for his extensive work in animation, including numerous roles in popular Cartoon Network and Disney series.
  • D. Bob Morton
    Bob Morton is a fictional corporate executive and ambitious OCP executive from the 1987 science fiction film "RoboCop."
  • E. Maurice LaMarche
    Maurice LaMarche is a Canadian-American voice actor renowned for his work in animation and video games, including iconic roles such as The Brain in "Pinky and the Brain."
  • 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_69d889e0385081908a04b66f4dd4bd0d completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4592ce42c8190a54a0a328c5e8ffc completed April 19, 2026, 4:25 a.m.
Created at: April 10, 2026, 5:50 a.m.