Triple

T6588402
Position Surface form Disambiguated ID Type / Status
Subject Carolinum E159285 entity
Predicate locatedInTheOldTown P15541 FINISHED
Object Old Town of Prague E291105 NE FINISHED

How this triple was built (3 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: Old Town of Prague | Statement: [Carolinum, locatedInTheOldTown, Old Town of Prague]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Old Town of Prague
Context triple: [Carolinum, locatedInTheOldTown, Old Town of Prague]
  • A. Historic Centre of Prague
    The Historic Centre of Prague is a UNESCO-listed medieval urban core of the Czech capital, renowned for its well-preserved Gothic, Renaissance, and Baroque architecture, including landmarks like Prague Castle and Old Town Square.
  • B. Old Town, Prague chosen
    Old Town, Prague is the historic medieval heart of the Czech capital, known for its cobbled streets, Gothic and Baroque architecture, and the famous Old Town Square with its Astronomical Clock.
  • C. Prague Castle
    Prague Castle is a historic fortress complex in Prague that served as the seat of Bohemian kings and Holy Roman Emperors and is now the official residence of the Czech president.
  • D. New Town, Prague
    New Town, Prague is a historic central district of the Czech capital known for its wide boulevards, major squares like Wenceslas Square, and a mix of medieval, neo-Renaissance, and modern architecture.
  • E. Old Town Hall, Prague
    Old Town Hall in Prague is a historic Gothic complex on the Old Town Square, renowned as a major city landmark and the site of the famous Prague Astronomical Clock.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locatedInTheOldTown
Context triple: [Carolinum, locatedInTheOldTown, Old Town of Prague]
  • A. locatedInOldCity chosen
    Indicates that an entity is situated within the boundaries of an old or historic part of a city.
  • B. locatedInOrNearModernSettlement
    Indicates that something is situated within or in close proximity to a present-day town, city, or other populated settlement.
  • C. isInHistoricCenterOf
    Indicates that one entity is located within the historic center area of another entity (typically a city or town).
  • D. hasCityCentreLocation
    Indicates that something is located in, or directly associated with, the central area of a city.
  • E. locatedInHistoricSite
    Indicates that an entity is situated within or on the grounds of a place officially recognized as a historic site.
  • F. None of above.

Provenance (4 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_69c688366ce8819083f8883983c0df92 completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6c07cdf048190945ca5810fb1de88 completed March 27, 2026, 5:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6d5794f388190a04f4f9c9e628f22 completed March 27, 2026, 7:07 p.m.
PD Predicate disambiguation batch_69c6acfb462481909cb7aff5af4bca9d completed March 27, 2026, 4:14 p.m.
Created at: March 27, 2026, 1:55 p.m.