Triple

T18548688
Position Surface form Disambiguated ID Type / Status
Subject Tiffany Stewart E453307 entity
Predicate spouse P13 FINISHED
Object Mark Cuban 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: Mark Cuban | Statement: [Tiffany Stewart, spouse, Mark Cuban]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Cuban
Context triple: [Tiffany Stewart, spouse, Mark Cuban]
  • A. Mark Cuban chosen
    Mark Cuban is an American billionaire entrepreneur, investor, and media personality best known as the outspoken owner of the NBA’s Dallas Mavericks and a longtime “Shark Tank” star.
  • B. David Tepper
    David Tepper is an American billionaire hedge fund manager and philanthropist, best known as the founder of Appaloosa Management and as a prominent NFL and MLS team owner.
  • C. Tim Connelly
    Tim Connelly is an American basketball executive known for leading NBA front offices, including his current role overseeing the Minnesota Timberwolves’ basketball operations.
  • D. Michael Kay
    Michael Kay is a New York sports broadcaster best known as the television play-by-play announcer for the New York Yankees and host of "The Michael Kay Show."
  • E. Daryl Morey
    Daryl Morey is an NBA executive and analytics pioneer best known for his influential tenure as a general manager with the Houston Rockets and his data-driven approach to team building.
  • 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_69d8d388b0c881908e610a1c45b52640 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e534be2298819095f637065fc2724e completed April 19, 2026, 8:02 p.m.
Created at: April 10, 2026, 11:38 a.m.