Triple

T22394164
Position Surface form Disambiguated ID Type / Status
Subject Adidas Conext19 E553585 entity
Predicate usedInCompetition P13690 FINISHED
Object 2019 K League 1 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: 2019 K League 1 | Statement: [Adidas Conext19, usedInCompetition, 2019 K League 1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 2019 K League 1
Context triple: [Adidas Conext19, usedInCompetition, 2019 K League 1]
  • A. K League 1 chosen
    K League 1 is the top professional football (soccer) division in South Korea, featuring the country’s highest-level clubs in a nationwide league competition.
  • B. K League 1 matches
    K League 1 matches are top-tier South Korean professional football league games featuring the country’s leading clubs.
  • C. Korean FA Cup
    The Korean FA Cup is South Korea’s premier national knockout football cup competition, featuring professional and amateur clubs from across the country.
  • D. K League 2
    K League 2 is the second tier of professional football in South Korea, serving as the division below the K League 1 in the national league system.
  • E. K League Federation
    The K League Federation is the organizing body responsible for overseeing South Korea’s professional football leagues and their member clubs.
  • 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_69e11e4cf87c8190a1ff474daec326b7 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1585ce39c819082b62e7f2e297d9b completed April 29, 2026, 1:01 a.m.
Created at: April 16, 2026, 8:45 p.m.