Triple

T16764503
Position Surface form Disambiguated ID Type / Status
Subject Prague 1 E407427 entity
Predicate borders P224 FINISHED
Object Prague 2 E393450 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: Prague 2 | Statement: [Prague 1, borders, Prague 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Prague 2
Context triple: [Prague 1, borders, Prague 2]
  • A. Prague 2 chosen
    Prague 2 is a central district of Prague, Czech Republic, known for its historic neighborhoods, parks, and landmarks such as Vyšehrad.
  • B. Prague 3
    Prague 3 is a central district of Prague known for its historic neighborhoods, including Žižkov, and notable cultural and religious sites such as the New Jewish Cemetery.
  • C. Prague 17
    Prague 17 is a municipal district of Prague, Czech Republic, located on the western edge of the city and encompassing primarily residential neighborhoods.
  • D. Prague 11
    Prague 11 is a municipal district in the southeastern part of Prague, Czech Republic, known largely for its extensive panel housing estates and residential neighborhoods such as Háje.
  • E. Prague 1
    Prague 1 is the historic central district of Prague, encompassing many of the city’s most famous landmarks, government buildings, and tourist attractions.
  • 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_69d8839174188190909f190097207065 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3abef492c8190880d3b39c3641eed completed April 18, 2026, 4:06 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00a52ff9d481909675c7e1f81191dc completed May 10, 2026, 3:33 p.m.
Created at: April 10, 2026, 5:21 a.m.