Triple

T19817620
Position Surface form Disambiguated ID Type / Status
Subject SK Slavia Prague E476100 entity
Predicate derby P3425 FINISHED
Object Prague derby 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: Prague derby | Statement: [SK Slavia Prague, derby, Prague derby]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prague derby
Context triple: [SK Slavia Prague, derby, Prague derby]
  • A. Prague derby chosen
    The Prague derby is the fiercely contested ice hockey rivalry between HC Slavia Praha and their main city opponents in Prague.
  • B. East Bohemian derby
    The East Bohemian derby is a regional football rivalry match between clubs from the East Bohemia area of the Czech Republic, notably featuring FK Pardubice.
  • C. Silesian derby
    The Silesian derby is a fiercely contested football rivalry match between major clubs from Poland’s Silesia region, most prominently Górnik Zabrze and their local adversaries.
  • D. Czech Cup
    The Czech Cup is the premier national knockout football competition in the Czech Republic, featuring clubs from various league levels.
  • E. Czech Supercup
    The Czech Supercup was an annual football match in the Czech Republic contested between the winners of the domestic league and national cup.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e654fac7b481909a19ae0d608e01d9 completed April 20, 2026, 4:31 p.m.
Created at: April 10, 2026, 1:50 p.m.