Triple

T17898248
Position Surface form Disambiguated ID Type / Status
Subject Kalani Brown E447489 entity
Predicate playedFor P2170 FINISHED
Object Atlanta Dream 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: Atlanta Dream | Statement: [Kalani Brown, playedFor, Atlanta Dream]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Atlanta Dream
Context triple: [Kalani Brown, playedFor, Atlanta Dream]
  • A. Atlanta Dream chosen
    The Atlanta Dream is a professional women's basketball team based in Atlanta, Georgia, that competes in the WNBA.
  • B. Washington Mystics
    The Washington Mystics are a professional women's basketball team based in Washington, D.C., competing in the WNBA.
  • C. Phoenix Mercury
    The Phoenix Mercury are a professional women's basketball team based in Phoenix, Arizona, competing in the WNBA and known for multiple championships and star players.
  • D. Houston Comets
    The Houston Comets were a dominant early WNBA franchise that won the league’s first four championships and featured stars like Cynthia Cooper and Sheryl Swoopes.
  • E. Dallas Wings
    The Dallas Wings are a professional women's basketball team in the WNBA based in the Dallas–Fort Worth area.
  • 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_69d8b9f59bd48190a6fc925a855b8bac completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e49d8122b481909992356f3f575858 completed April 19, 2026, 9:16 a.m.
Created at: April 10, 2026, 10:19 a.m.