Triple

T2995386
Position Surface form Disambiguated ID Type / Status
Subject Ballers E81052 entity
Predicate castMember P1668 FINISHED
Object Rob Corddry E372232 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: Rob Corddry | Statement: [Ballers, castMember, Rob Corddry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rob Corddry
Context triple: [Ballers, castMember, Rob Corddry]
  • A. Rob Corddry chosen
    Rob Corddry is an American actor and comedian best known for his work on "The Daily Show" and in films like "Hot Tub Time Machine."
  • B. Nick Kroll
    Nick Kroll is an American comedian, actor, writer, and producer known for his sketch series "Kroll Show," his work on "The League," and co-creating and voicing characters in the animated series "Big Mouth."
  • C. Joel McHale
    Joel McHale is an American actor, comedian, and television host best known for leading the satirical series "The Soup" and starring on the sitcom "Community."
  • D. Paul Lieberstein
    Paul Lieberstein is an American writer, producer, and actor best known for playing HR representative Toby Flenderson and serving as a key writer and showrunner on the U.S. version of "The Office."
  • E. Rob Riggle
    Rob Riggle is an American actor, comedian, and former Marine officer known for his energetic, often over-the-top roles in film and television comedies.
  • 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_69ad8b187fc8819085914d3c9ea3142d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad99f2e5888190b3346012e2578dab completed March 8, 2026, 3:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4e4c7f8c4819097be8b80d4064806 completed March 14, 2026, 4:32 a.m.
Created at: March 8, 2026, 2:59 p.m.