Triple

T20231339
Position Surface form Disambiguated ID Type / Status
Subject SaiPa E495531 entity
Predicate playsIn P795 FINISHED
Object Liiga 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: Liiga | Statement: [SaiPa, playsIn, Liiga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Liiga
Context triple: [SaiPa, playsIn, Liiga]
  • A. SM-liiga chosen
    SM-liiga is the top professional ice hockey league in Finland, featuring the country’s premier teams and players.
  • B. Elitserien
    Elitserien is the top professional bandy league in Sweden, featuring the country's highest-level clubs competing for the national championship.
  • C. Veikkausliiga
    Veikkausliiga is the top professional football league in Finland, featuring the country’s highest-level clubs in the sport.
  • D. Swedish Hockey League
    The Swedish Hockey League is Sweden's top professional ice hockey league and one of Europe's premier hockey competitions, known for developing many NHL-caliber players.
  • E. Mestis and Suomi-sarja
    Mestis and Suomi-sarja are the second- and third-tier Finnish men’s ice hockey leagues that form a key developmental and competitive bridge beneath the country’s top professional level.
  • 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_69da626cff80819097b530718a7c98b6 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66fddafac819089cef4158f5e0ab5 completed April 20, 2026, 6:26 p.m.
Created at: April 11, 2026, 11:39 p.m.