Triple

T5731049
Position Surface form Disambiguated ID Type / Status
Subject Kat Dennings E126383 entity
Predicate televisionSeries P3279 FINISHED
Object 2 Broke Girls E539593 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: 2 Broke Girls | Statement: [Kat Dennings, televisionSeries, 2 Broke Girls]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 2 Broke Girls
Context triple: [Kat Dennings, televisionSeries, 2 Broke Girls]
  • A. 2 Broke Girls chosen
    2 Broke Girls is an American sitcom that follows the comedic misadventures of two financially struggling waitresses trying to start a cupcake business in Brooklyn.
  • B. New Girl in Town
    New Girl in Town is a 1957 Broadway musical adaptation of Eugene O’Neill’s play "Anna Christie," best known for its Tony-winning star turn by Gwen Verdon.
  • C. New Girl
    New Girl is an American sitcom that follows the quirky misadventures of Jess Day and her three male roommates in a Los Angeles loft.
  • D. Good Girls
    Good Girls is an American dark comedy-drama television series about three suburban mothers who turn to crime to solve their financial problems.
  • E. Scream Queens
    Scream Queens is a satirical horror-comedy television series that blends slasher tropes with dark humor and a college sorority setting.
  • 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_69c0083082288190b7478cead6b5430a completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c025318d688190bd878c5aa1a28728 completed March 22, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07dffe45481909eb617e40c83bd14 completed March 22, 2026, 11:40 p.m.
Created at: March 22, 2026, 3:47 p.m.