Triple

T17390366
Position Surface form Disambiguated ID Type / Status
Subject Ben Cafferty E422804 entity
Predicate appearsIn P795 FINISHED
Object Veep 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: Veep | Statement: [Ben Cafferty, appearsIn, Veep]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Veep
Context triple: [Ben Cafferty, appearsIn, Veep]
  • A. Veep chosen
    Veep is an American political satire television series that follows the inept and often chaotic career of a fictional U.S. vice president and later president, Selina Meyer.
  • B. Parks and Recreation
    Parks and Recreation is an American mockumentary-style sitcom that follows the quirky employees of a small-town parks department in the fictional town of Pawnee, Indiana.
  • C. West Wing
    West Wing is a major building within St Thomas’ Hospital in London that houses key clinical and support services for patients.
  • D. West Wing
    The West Wing is the section of the White House that houses the Oval Office and the primary offices of the President of the United States and senior staff.
  • E. West Wing
    The West Wing is a major gallery section of the Cleveland Museum of Art that houses part of its art collections and exhibitions.
  • 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_69d889d710288190bf0f4762801fefae completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43ab950d4819098d6a46f67c46191 completed April 19, 2026, 2:15 a.m.
Created at: April 10, 2026, 5:45 a.m.