Triple

T1748911
Position Surface form Disambiguated ID Type / Status
Subject Cats (2019 film) E38394 entity
Predicate stars P1956 FINISHED
Object James Corden E126640 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: James Corden | Statement: [Cats (2019 film), stars, James Corden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Corden
Context triple: [Cats (2019 film), stars, James Corden]
  • A. James Corden chosen
    James Corden is a British actor, comedian, and television host best known internationally for presenting "The Late Late Show with James Corden" and creating and starring in the sitcom "Gavin & Stacey."
  • B. Jimmy Fallon
    Jimmy Fallon is an American comedian, actor, and television host best known for hosting NBC’s "The Tonight Show Starring Jimmy Fallon."
  • C. Trevor Noah
    Trevor Noah is a South African comedian, writer, and television host best known for anchoring Comedy Central’s satirical news program "The Daily Show."
  • D. Craig Ferguson
    Craig Ferguson is a Scottish-American comedian, actor, writer, and television host best known for hosting CBS’s "The Late Late Show with Craig Ferguson."
  • E. Neil Patrick Harris
    Neil Patrick Harris is an American actor, comedian, and magician best known for his roles in the TV series "How I Met Your Mother" and "Doogie Howser, M.D."
  • 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_69a8862b01a48190ab47209063af82d9 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69aa63ee4d2081909dfd6d3244228c56 completed March 6, 2026, 5:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ada0e21e58819082943212bd725581 completed March 8, 2026, 4:16 p.m.
Created at: March 4, 2026, 7:31 p.m.