Triple

T16223837
Position Surface form Disambiguated ID Type / Status
Subject Wallenstein Palace E393793 entity
Predicate near P350 FINISHED
Object Malostranské náměstí E646022 NE FINISHED

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: Malostranské náměstí | Statement: [Wallenstein Palace, near, Malostranské náměstí]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Malostranské náměstí
Context triple: [Wallenstein Palace, near, Malostranské náměstí]
  • A. Malostranské náměstí chosen
    Malostranské náměstí is a historic square in Prague’s Lesser Town known for its Baroque architecture, churches, and role as a central hub beneath Prague Castle.
  • B. Hradčanské náměstí
    Hradčanské náměstí is a historic square in Prague situated by Prague Castle, known for its grand palaces, churches, and panoramic city views.
  • C. Husovo náměstí
    Husovo náměstí is the central historic town square of Beroun in the Czech Republic, known for its traditional architecture and local civic life.
  • 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. Jiráskovo náměstí
    Jiráskovo náměstí is a square in Prague, Czech Republic, located along the Vltava River and known for its central location and notable surrounding architecture.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d87f204df88190a8f88923decf9835 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e23d23e63881908806920d878f2adb completed April 17, 2026, 2:01 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00456f2ba481909f243ab2c4619623 completed May 10, 2026, 8:44 a.m.
Created at: April 10, 2026, 5:03 a.m.