Triple

T10939367
Position Surface form Disambiguated ID Type / Status
Subject Sanok E258423 entity
Predicate hasTwinTown P919 FINISHED
Object Snina
Snina is a town in eastern Slovakia known as a gateway to the Poloniny National Park and the easternmost regions of the country.
 E895258 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: Snina | Statement: [Sanok, hasTwinTown, Snina]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Snina
Context triple: [Sanok, hasTwinTown, Snina]
  • A. Lučina
    Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
  • B. Bregava
    Bregava is a river in Bosnia and Herzegovina known for flowing through the town of Stolac before joining the Neretva River.
  • C. Sesia
    The Sesia is a river in northwestern Italy that flows through the Piedmont region before joining the Po River.
  • D. Sedova
    Sedova is a Russian surname most notably associated with revolutionary figure Natalia Sedova, the second wife of Leon Trotsky.
  • E. Bílina
    Bílina is a river in the Czech Republic that flows through the Ústí nad Labem Region and is known for passing through several industrial and mining areas.
  • 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: Snina
Triple: [Sanok, hasTwinTown, Snina]
Generated description
Snina is a town in eastern Slovakia known as a gateway to the Poloniny National Park and the easternmost regions of the country.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Snina
Target entity description: Snina is a town in eastern Slovakia known as a gateway to the Poloniny National Park and the easternmost regions of the country.
  • A. Lučina
    Lučina is a river in the Moravian-Silesian Region of the Czech Republic that flows through the city of Ostrava.
  • B. Bregava
    Bregava is a river in Bosnia and Herzegovina known for flowing through the town of Stolac before joining the Neretva River.
  • C. Sesia
    The Sesia is a river in northwestern Italy that flows through the Piedmont region before joining the Po River.
  • D. Sedova
    Sedova is a Russian surname most notably associated with revolutionary figure Natalia Sedova, the second wife of Leon Trotsky.
  • E. Bílina
    Bílina is a river in the Czech Republic that flows through the Ústí nad Labem Region and is known for passing through several industrial and mining areas.
  • 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_69d6aa8769b4819082bfe5e61b9017f0 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d770c1389881909341170984211810 completed April 9, 2026, 9:26 a.m.
NED1 Entity disambiguation (via context triple) batch_69e23c0e940081908c84ea4cf3b877fc completed April 17, 2026, 1:56 p.m.
NEDg Description generation batch_69e24541cbb481908f14a9cb2787c118 completed April 17, 2026, 2:35 p.m.
NED2 Entity disambiguation (via description) batch_69e248f48dc88190af9491e8cdc4a532 completed April 17, 2026, 2:51 p.m.
Created at: April 8, 2026, 9:23 p.m.