Triple

T1056806
Position Surface form Disambiguated ID Type / Status
Subject Josiah Bartlet E22813 entity
Predicate creator P184 FINISHED
Object Aaron Sorkin E22517 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: Aaron Sorkin | Statement: [Josiah Bartlet, creator, Aaron Sorkin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aaron Sorkin
Context triple: [Josiah Bartlet, creator, Aaron Sorkin]
  • A. Aaron Sorkin chosen
    Aaron Sorkin is an American screenwriter, playwright, and director renowned for his fast-paced, dialogue-driven dramas in film, television, and theater.
  • B. Dustin Lance Black
    Dustin Lance Black is an American screenwriter, director, and LGBT rights activist best known for his Oscar-winning screenplay for the film "Milk."
  • C. Akiva Goldsman
    Akiva Goldsman is an American screenwriter, producer, and director known for his work on major Hollywood films such as A Beautiful Mind, for which he won an Academy Award for Best Adapted Screenplay.
  • D. Beau Willimon
    Beau Willimon is an American playwright, screenwriter, and producer best known for developing the U.S. version of the political drama series "House of Cards."
  • E. Mitchell Hurwitz
    Mitchell Hurwitz is an American television writer and producer best known for creating the critically acclaimed sitcom "Arrested Development."
  • 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_69a493dada0481909c43649f9843ea91 completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b8da80dc8190b79beaf509910725 completed March 1, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac5999d30881909bc9e2d8528b1b56 completed March 7, 2026, 5 p.m.
Created at: March 1, 2026, 7:42 p.m.