Triple

T17709758
Position Surface form Disambiguated ID Type / Status
Subject Sviatoshynsko–Brovarska line E441531 entity
Predicate hasStation P35 FINISHED
Object Beresteiska
Beresteiska is a metro station in Kyiv, Ukraine, located on the Sviatoshynsko–Brovarska line of the Kyiv Metro system.
 E1284032 NE FINISHED

How this triple was built (4 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: Beresteiska | Statement: [Sviatoshynsko–Brovarska line, hasStation, Beresteiska]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Beresteiska
Context triple: [Sviatoshynsko–Brovarska line, hasStation, Beresteiska]
  • A. Parhae
    Parhae was a multi-ethnic kingdom that flourished in Northeast Asia from the late 7th to early 10th century, occupying parts of Manchuria, the Korean Peninsula, and the Russian Far East.
  • B. Bällsta
    Bällsta is a small locality in eastern central Sweden situated within Vallentuna Municipality in Stockholm County.
  • C. Vårsta
    Vårsta is a small locality in eastern Sweden, situated within Botkyrka Municipality in Stockholm County.
  • D. Märsta
    Märsta is a town in Stockholm County, Sweden, known as a residential and transport hub near Stockholm Arlanda Airport.
  • E. Baskinta
    Baskinta is a picturesque Lebanese mountain village known for its scenic landscapes, cool climate, and rich literary and cultural heritage.
  • 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: Beresteiska
Triple: [Sviatoshynsko–Brovarska line, hasStation, Beresteiska]
Generated description
Beresteiska is a metro station in Kyiv, Ukraine, located on the Sviatoshynsko–Brovarska line of the Kyiv Metro system.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Beresteiska
Target entity description: Beresteiska is a metro station in Kyiv, Ukraine, located on the Sviatoshynsko–Brovarska line of the Kyiv Metro system.
  • A. Parhae
    Parhae was a multi-ethnic kingdom that flourished in Northeast Asia from the late 7th to early 10th century, occupying parts of Manchuria, the Korean Peninsula, and the Russian Far East.
  • B. Bällsta
    Bällsta is a small locality in eastern central Sweden situated within Vallentuna Municipality in Stockholm County.
  • C. Vårsta
    Vårsta is a small locality in eastern Sweden, situated within Botkyrka Municipality in Stockholm County.
  • D. Märsta
    Märsta is a town in Stockholm County, Sweden, known as a residential and transport hub near Stockholm Arlanda Airport.
  • E. Baskinta
    Baskinta is a picturesque Lebanese mountain village known for its scenic landscapes, cool climate, and rich literary and cultural heritage.
  • F. None of above. chosen

Provenance (5 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4729a9a9c81908d65ff0bda12c961 completed April 19, 2026, 6:13 a.m.
NED1 Entity disambiguation (via context triple) batch_6a023025ae808190ba3e9a875bfc68e9 completed May 11, 2026, 7:38 p.m.
NEDg Description generation batch_6a023249cfb0819091d3fa8c3089f241 completed May 11, 2026, 7:47 p.m.
NED2 Entity disambiguation (via description) batch_6a0232ce696c81908d0e57ea214f88ce completed May 11, 2026, 7:49 p.m.
Created at: April 10, 2026, 10:05 a.m.