Triple

T3621489
Position Surface form Disambiguated ID Type / Status
Subject Semi-Pro E76736 entity
Predicate starring P1507 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: [Semi-Pro, starring, Rob Corddry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rob Corddry
Context triple: [Semi-Pro, starring, 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. Andy Richter
    Andy Richter is an American comedian and actor best known as Conan O’Brien’s longtime talk-show sidekick and for his roles in various film and television comedies.
  • E. Paul F. Tompkins
    Paul F. Tompkins is an American comedian, actor, and writer known for his stand-up, podcast appearances, and character roles in television and film.
  • 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_69ad85dae2fc81908d1ceadbc6af0089 completed March 8, 2026, 2:21 p.m.
NER Named-entity recognition batch_69adc2b9aa608190a680b250ecf63156 completed March 8, 2026, 6:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69b66b21271c81909f1cf3239bc1b7eb completed March 15, 2026, 8:17 a.m.
Created at: March 8, 2026, 3:23 p.m.