Triple

T17767862
Position Surface form Disambiguated ID Type / Status
Subject Alexander Nevsky Square E443555 entity
Predicate hasPublicTransportConnection P3791 FINISHED
Object Sofia trolleybus network NE NERFINISHED

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: Sofia trolleybus network | Statement: [Alexander Nevsky Square, hasPublicTransportConnection, Sofia trolleybus network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sofia trolleybus network
Context triple: [Alexander Nevsky Square, hasPublicTransportConnection, Sofia trolleybus network]
  • A. Sofia tram network
    The Sofia tram network is an extensive urban tramway system serving Bulgaria’s capital city, providing key public transportation links across Sofia.
  • B. Sofia Metro
    Sofia Metro is the rapid transit system serving Bulgaria’s capital city, providing high-capacity urban rail transport across Sofia and its metropolitan area.
  • C. Saint Petersburg trolleybus network
    The Saint Petersburg trolleybus network is an extensive electric public transport system in Saint Petersburg, Russia, operating trolleybuses along city streets and serving as a major component of the urban transit infrastructure.
  • D. Moscow trolleybus network
    The Moscow trolleybus network was an extensive electric public transport system in Moscow, once one of the largest of its kind in the world, operating trolleybuses across the city until its closure in the late 2010s.
  • E. Crimean trolleybus line
    The Crimean trolleybus line is a long-distance electric trolleybus route in Crimea, notable for being one of the world’s longest trolleybus lines and connecting cities such as Simferopol, Alushta, and Yalta across mountainous terrain.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sofia trolleybus network
Target entity description: The Sofia trolleybus network is an electric public transport system in Bulgaria's capital, operating multiple trolleybus lines that connect key urban areas and residential districts across the city.
  • A. Sofia tram network
    The Sofia tram network is an extensive urban tramway system serving Bulgaria’s capital city, providing key public transportation links across Sofia.
  • B. Sofia Metro
    Sofia Metro is the rapid transit system serving Bulgaria’s capital city, providing high-capacity urban rail transport across Sofia and its metropolitan area.
  • C. Saint Petersburg trolleybus network
    The Saint Petersburg trolleybus network is an extensive electric public transport system in Saint Petersburg, Russia, operating trolleybuses along city streets and serving as a major component of the urban transit infrastructure.
  • D. Moscow trolleybus network
    The Moscow trolleybus network was an extensive electric public transport system in Moscow, once one of the largest of its kind in the world, operating trolleybuses across the city until its closure in the late 2010s.
  • E. Crimean trolleybus line
    The Crimean trolleybus line is a long-distance electric trolleybus route in Crimea, notable for being one of the world’s longest trolleybus lines and connecting cities such as Simferopol, Alushta, and Yalta across mountainous terrain.
  • F. None of above. chosen

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_69d8b9edf16c8190a59ebd245d378f4f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e485fd8aa081909c8ee9264af15c69 completed April 19, 2026, 7:36 a.m.
Created at: April 10, 2026, 10:11 a.m.