Triple

T2392926
Position Surface form Disambiguated ID Type / Status
Subject Jennifer Azzi E48982 entity
Predicate league P888 FINISHED
Object WNBA E15646 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: WNBA | Statement: [Jennifer Azzi, league, WNBA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: WNBA
Context triple: [Jennifer Azzi, league, WNBA]
  • A. Women’s National Basketball Association chosen
    The Women’s National Basketball Association (WNBA) is the premier professional women’s basketball league in the United States, featuring top female players from around the world.
  • B. WNBA Finals
    The WNBA Finals is the culminating postseason series that determines the champion of the Women's National Basketball Association each year.
  • C. WNBA All-Star Game
    The WNBA All-Star Game is the league’s annual midseason exhibition showcasing its top players in a fan-focused, entertainment-driven matchup.
  • D. WNBA Draft
    The WNBA Draft is the annual event where Women's National Basketball Association teams select eligible college and international players to join the league.
  • E. Western Conference (WNBA)
    The Western Conference (WNBA) is one of the league’s two conferences, grouping together several of its teams for regular-season standings and playoff seeding.
  • 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_69a88aa5f63081908d07fd302029fcbd completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc876d48881909e4d6f5ebe430012 completed March 7, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69af177b898c8190bee910be75e93f6c completed March 9, 2026, 6:54 p.m.
Created at: March 4, 2026, 7:57 p.m.