Triple

T18457242
Position Surface form Disambiguated ID Type / Status
Subject Sosva E450933 entity
Predicate hasNameInLanguage P15 FINISHED
Object Сосьва
Сосьва — это река и одноимённый посёлок в Свердловской области России, расположенные в бассейне Северной Сосьвы.
 E1325133 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: Сосьва | Statement: [Sosva, hasNameInLanguage, Сосьва]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Сосьва
Context triple: [Sosva, hasNameInLanguage, Сосьва]
  • A. Sosnytsia
    Sosnytsia is a small historic town in northern Ukraine known for its traditional architecture and rural character.
  • B. Sontsovka
    Sontsovka is a rural locality in present-day Ukraine best known as the birthplace of the composer Sergei Prokofiev.
  • C. Verkhovyna
    Verkhovyna is a mountainous village and popular tourist destination in the Carpathian region of western Ukraine, known for its Hutsul culture and scenic landscapes.
  • D. Medveditsa
    Medveditsa is a river in southwestern Russia that flows through the Volgograd and Saratov regions before joining the Don River.
  • E. Савиндан
    Савиндан је српски православни празник посвећен Светом Сави, првом архиепископу и просветитељу српског народа, који се обележава као школска и црквена слава.
  • 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: Сосьва
Triple: [Sosva, hasNameInLanguage, Сосьва]
Generated description
Сосьва — это река и одноимённый посёлок в Свердловской области России, расположенные в бассейне Северной Сосьвы.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Сосьва
Target entity description: Сосьва — это река и одноимённый посёлок в Свердловской области России, расположенные в бассейне Северной Сосьвы.
  • A. Sosnytsia
    Sosnytsia is a small historic town in northern Ukraine known for its traditional architecture and rural character.
  • B. Sontsovka
    Sontsovka is a rural locality in present-day Ukraine best known as the birthplace of the composer Sergei Prokofiev.
  • C. Verkhovyna
    Verkhovyna is a mountainous village and popular tourist destination in the Carpathian region of western Ukraine, known for its Hutsul culture and scenic landscapes.
  • D. Medveditsa
    Medveditsa is a river in southwestern Russia that flows through the Volgograd and Saratov regions before joining the Don River.
  • E. Савиндан
    Савиндан је српски православни празник посвећен Светом Сави, првом архиепископу и просветитељу српског народа, који се обележава као школска и црквена слава.
  • 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_69d8d38345688190b565eac2e4cd7935 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5264ce5948190b57baa2ea71297a9 completed April 19, 2026, 7 p.m.
NED1 Entity disambiguation (via context triple) batch_6a040fe9a7748190b23d40466c3a314a completed May 13, 2026, 5:45 a.m.
NEDg Description generation batch_6a0412260e448190acf29d53559ab69d completed May 13, 2026, 5:54 a.m.
NED2 Entity disambiguation (via description) batch_6a04130734688190a2803c7037900269 completed May 13, 2026, 5:58 a.m.
Created at: April 10, 2026, 11:31 a.m.