Triple

T21598217
Position Surface form Disambiguated ID Type / Status
Subject Sazka Arena E532958 entity
Predicate locatedIn P40 FINISHED
Object Prague 9 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 9 | Statement: [Sazka Arena, locatedIn, Prague 9]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Prague 9
Context triple: [Sazka Arena, locatedIn, Prague 9]
  • A. Prague 9 chosen
    Prague 9 is a municipal district of Prague in the Czech Republic, known for its mix of residential areas, industrial zones, and major venues such as large sports and entertainment arenas.
  • B. Prague 10
    Prague 10 is one of the administrative districts of Prague, Czech Republic, encompassing mainly residential neighborhoods and parts of the city’s eastern area.
  • C. Prague 8
    Prague 8 is a municipal district of Prague that includes a mix of historic neighborhoods and modern residential and commercial areas along the northeastern part of the city.
  • D. Prague 5
    Prague 5 is a large municipal district of Prague known for its mix of residential neighborhoods, commercial areas, and green spaces on the western side of the city.
  • E. Prague 7
    Prague 7 is a municipal district of Prague, Czech Republic, known for its residential neighborhoods, parks, and cultural institutions along the Vltava River.
  • 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_69e0c46364608190a337dc8720dc2a35 completed April 16, 2026, 11:13 a.m.
NER Named-entity recognition batch_69eefae2fc908190b989f39e8cefffb2 completed April 27, 2026, 5:57 a.m.
Created at: April 16, 2026, 6:32 p.m.