Triple

T6625733
Position Surface form Disambiguated ID Type / Status
Subject Białystok railway station E149794 entity
Predicate connectsTo P845 FINISHED
Object Sokółka E287212 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: Sokółka | Statement: [Białystok railway station, connectsTo, Sokółka]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sokółka
Context triple: [Białystok railway station, connectsTo, Sokółka]
  • A. Sokółka chosen
    Sokółka is a small town in northeastern Poland known for its location in the Podlasie region near the border with Belarus.
  • B. Sokołówka
    Sokołówka is a small river in Poland known for flowing through the city of Łódź and its surrounding areas.
  • C. Kurzętnik
    Kurzętnik is a village in northern Poland known for its historical character and location within the picturesque Warmian-Masurian region.
  • D. Sukiennice
    Sukiennice is a historic Renaissance cloth hall and landmark market building located in the main square of Kraków, Poland.
  • E. Ciechocinek
    Ciechocinek is a Polish spa town renowned for its historic saline graduation towers and therapeutic health resorts.
  • 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_69c687ee50048190aa151765bef16193 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6af8187d881908b7a86f2cae5de23 completed March 27, 2026, 4:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6eee8740881908b4fafb12db6b7f3 completed March 27, 2026, 8:56 p.m.
Created at: March 27, 2026, 1:58 p.m.