Triple

T19244804
Position Surface form Disambiguated ID Type / Status
Subject Třeboň E481221 entity
Predicate hasLandmark P105 FINISHED
Object Masaryk Square 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: Masaryk Square | Statement: [Třeboň, hasLandmark, Masaryk Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Masaryk Square
Context triple: [Třeboň, hasLandmark, Masaryk Square]
  • A. Masaryk Square chosen
    Masaryk Square is the central historic town square and main public gathering place in the Czech town of Uherské Hradiště.
  • B. Václavské náměstí
    Václavské náměstí is a major historic square and commercial center in Prague, renowned as a traditional site of national gatherings, demonstrations, and key moments in Czech history.
  • C. Madách Square
    Madách Square is a notable public square in central Budapest known for its distinctive 1930s architectural ensemble and role as a gateway to the city’s historic Jewish Quarter.
  • D. Karlovo náměstí
    Karlovo náměstí is a major metro station and public square in central Prague, known as an important transport hub and urban landmark.
  • E. Wenceslas Square
    Wenceslas Square is a major historic boulevard and commercial center in Prague, renowned as a focal point for political demonstrations and public gatherings in Czech history.
  • 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_69d8e8cd9d1081908a181d02b88b59b8 completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e5faf47820819081e8b6af852bb1dd completed April 20, 2026, 10:07 a.m.
Created at: April 10, 2026, 1:27 p.m.