Triple

T3942604
Position Surface form Disambiguated ID Type / Status
Subject Atlanta Dream E92068 entity
Predicate hasRivalryWith P893 FINISHED
Object Chicago Sky E66017 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: Chicago Sky | Statement: [Atlanta Dream, hasRivalryWith, Chicago Sky]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Chicago Sky
Context triple: [Atlanta Dream, hasRivalryWith, Chicago Sky]
  • A. Chicago Sky chosen
    The Chicago Sky are a professional women's basketball team based in Chicago that competes in the WNBA and has featured star players such as Elena Delle Donne.
  • B. New York Skyliners
    The New York Skyliners were a short-lived professional American football team that played home games at Shea Stadium in New York City during the 1960s.
  • C. Chicago Stags
    The Chicago Stags were a professional basketball team based in Chicago that competed in the late 1940s and early NBA era before folding in 1950.
  • D. Kansas City Wiz
    Kansas City Wiz was the original name of the Major League Soccer club now known as Sporting Kansas City.
  • 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 (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_69aed965502c8190904ebad1203a4ae8 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeedff736c8190b22e03d94c40f61a completed March 9, 2026, 3:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69b533912bf881909e5e5e9e4245edbf completed March 14, 2026, 10:08 a.m.
Created at: March 9, 2026, 3:24 p.m.