Triple

T3869300
Position Surface form Disambiguated ID Type / Status
Subject Ohře E91943 entity
Predicate flowsThrough P225 FINISHED
Object Sokolov
Sokolov is a town in the Karlovy Vary Region of the Czech Republic, known for its historical center and location in the Ohře River valley.
E394625 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: Sokolov | Statement: [Ohře, flowsThrough, Sokolov]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sokolov
Context triple: [Ohře, flowsThrough, Sokolov]
  • A. Ruzinov
    Ružinov is a borough of Bratislava, Slovakia, known as a major residential and commercial district of the capital.
  • B. Slaný
    Slaný is a historic town in the Czech Republic known for its medieval center and location northwest of Prague.
  • C. Nymburk
    Nymburk is a historic town in the Czech Republic known for its medieval fortifications and location on the Elbe River.
  • D. Karviná
    Karviná is an industrial city in the Moravian-Silesian Region of the Czech Republic, historically part of Cieszyn Silesia and known for its coal mining heritage.
  • E. Sušice
    Sušice is a town in the Czech Republic known as a local administrative, cultural, and tourist center in the southwestern Plzeň Region.
  • 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: Sokolov
Triple: [Ohře, flowsThrough, Sokolov]
Generated description
Sokolov is a town in the Karlovy Vary Region of the Czech Republic, known for its historical center and location in the Ohře River valley.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sokolov
Target entity description: Sokolov is a town in the Karlovy Vary Region of the Czech Republic, known for its historical center and location in the Ohře River valley.
  • A. Ruzinov
    Ružinov is a borough of Bratislava, Slovakia, known as a major residential and commercial district of the capital.
  • B. Slaný
    Slaný is a historic town in the Czech Republic known for its medieval center and location northwest of Prague.
  • C. Nymburk
    Nymburk is a historic town in the Czech Republic known for its medieval fortifications and location on the Elbe River.
  • D. Karviná
    Karviná is an industrial city in the Moravian-Silesian Region of the Czech Republic, historically part of Cieszyn Silesia and known for its coal mining heritage.
  • E. Sušice
    Sušice is a town in the Czech Republic known as a local administrative, cultural, and tourist center in the southwestern Plzeň Region.
  • 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_69aed9645f348190a9868e7cef56ab7e completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeec533828819080f52dae15fdbecd completed March 9, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b512440b8c8190ae2048bfcdd565ec completed March 14, 2026, 7:46 a.m.
NEDg Description generation batch_69b512f4041081908eb32ae059681afa completed March 14, 2026, 7:49 a.m.
NED2 Entity disambiguation (via description) batch_69b5137200a08190bd2a78398e03803e completed March 14, 2026, 7:51 a.m.
Created at: March 9, 2026, 3:20 p.m.