Triple

T14016199
Position Surface form Disambiguated ID Type / Status
Subject My Girl E337209 entity
Predicate castMember P1668 FINISHED
Object Griffin Dunne E387968 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: Griffin Dunne | Statement: [My Girl, castMember, Griffin Dunne]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Griffin Dunne
Context triple: [My Girl, castMember, Griffin Dunne]
  • A. Griffin Dunne chosen
    Griffin Dunne is an American actor, director, and producer known for roles in films like "An American Werewolf in London" and "After Hours."
  • B. Andrew Dorff
    Andrew Dorff was an American country music songwriter known for penning hits for artists such as Blake Shelton, Kenny Chesney, and Rascal Flatts.
  • C. Gil Pender
    Gil Pender is the nostalgic, time-traveling screenwriter protagonist of Woody Allen’s film "Midnight in Paris," portrayed by Owen Wilson.
  • D. William Devane
    William Devane is an American actor known for his intense, often authoritative roles in film and television, including prominent performances in projects like "Knots Landing" and "24."
  • E. Jon Cryer
    Jon Cryer is an American actor best known for his role as Alan Harper on the sitcom "Two and a Half Men" and for his work in films like "Pretty in Pink."
  • 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_69d81c6543a48190bd5ba93d7419e797 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de2f396b648190927e5718c3bb6511 completed April 14, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69fbacac12608190a5e3d970ec3cda45 completed May 6, 2026, 9:03 p.m.
Created at: April 9, 2026, 10:19 p.m.