Triple

T7741144
Position Surface form Disambiguated ID Type / Status
Subject Krasnodar E175511 entity
Predicate hasTrolleybusSystem P78434 FINISHED
Object Krasnodar trolleybus
The Krasnodar trolleybus is an electric public transport network serving the Russian city of Krasnodar, operating trolleybus routes across its urban areas.
E686413 NE FINISHED

How this triple was built (5 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: Krasnodar trolleybus | Statement: [Krasnodar, hasTrolleybusSystem, Krasnodar trolleybus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Krasnodar trolleybus
Context triple: [Krasnodar, hasTrolleybusSystem, Krasnodar trolleybus]
  • A. Volgograd trolleybus network
    The Volgograd trolleybus network is an electric public transit system in Volgograd, Russia, providing urban transportation via trolleybuses powered by overhead wires.
  • B. 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.
  • C. Volgograd tram network
    The Volgograd tram network is an extensive urban tramway system serving the Russian city of Volgograd, providing surface-level public transport that complements the partially grade-separated Volgograd Metrotram.
  • D. Volgograd Metrotram
    The Volgograd Metrotram is a hybrid light rail and underground tram system in Volgograd, Russia, providing rapid transit-style service along a dedicated north–south corridor through the city.
  • E. 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.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Krasnodar trolleybus
Triple: [Krasnodar, hasTrolleybusSystem, Krasnodar trolleybus]
Generated description
The Krasnodar trolleybus is an electric public transport network serving the Russian city of Krasnodar, operating trolleybus routes across its urban areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Krasnodar trolleybus
Target entity description: The Krasnodar trolleybus is an electric public transport network serving the Russian city of Krasnodar, operating trolleybus routes across its urban areas.
  • A. Volgograd trolleybus network
    The Volgograd trolleybus network is an electric public transit system in Volgograd, Russia, providing urban transportation via trolleybuses powered by overhead wires.
  • B. 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.
  • C. Volgograd tram network
    The Volgograd tram network is an extensive urban tramway system serving the Russian city of Volgograd, providing surface-level public transport that complements the partially grade-separated Volgograd Metrotram.
  • D. Volgograd Metrotram
    The Volgograd Metrotram is a hybrid light rail and underground tram system in Volgograd, Russia, providing rapid transit-style service along a dedicated north–south corridor through the city.
  • E. 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.
  • F. None of above. chosen
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasTrolleybusSystem
Context triple: [Krasnodar, hasTrolleybusSystem, Krasnodar trolleybus]
  • A. hasTrolleybusLine
    Indicates that there exists a trolleybus service or route connecting the related entities.
  • B. hasTramway
    Indicates that a location or area is served by, contains, or is connected to a tramway system.
  • C. hasBusServices
    Indicates that one location or entity is served by bus routes or bus transportation provided by another.
  • D. hasBRTLine
    Indicates that a bus rapid transit (BRT) line is present, operates on, or serves the referenced entity.
  • E. isPublicTransportBackboneOf
    Indicates that one transport system serves as the primary structural and functional core of a region’s overall public transportation network.
  • F. None of above. chosen

Provenance (7 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_69c6995f9c60819092e386192bd63c6f completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c70402169481909b219dc5f4a64b9b completed March 27, 2026, 10:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be454e708190b410dada4f4f1e97 completed March 29, 2026, 5:53 a.m.
NEDg Description generation batch_69c8bface14c8190a78d7ed43316bffd completed March 29, 2026, 5:59 a.m.
NED2 Entity disambiguation (via description) batch_69c8c02e7a548190b2c5ad84e4c3f1fb completed March 29, 2026, 6:01 a.m.
PD Predicate disambiguation batch_69c7016c4a748190a7012030edaefcee completed March 27, 2026, 10:15 p.m.
PDg Predicate description generation batch_69c7040091608190a9e46ecfb2ff0bca completed March 27, 2026, 10:26 p.m.
Created at: March 27, 2026, 4:07 p.m.