Triple

T12728451
Position Surface form Disambiguated ID Type / Status
Subject Korchevskoy Uyezd E304168 entity
Predicate capital P234 FINISHED
Object Korcheva
Korcheva was a historical town in the Tver region of Russia that served as an administrative center before being submerged by the Ivankovo Reservoir in the 1930s.
E1001657 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: Korcheva | Statement: [Korchevskoy Uyezd, capital, Korcheva]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Korcheva
Context triple: [Korchevskoy Uyezd, capital, Korcheva]
  • A. Korotkova
    Korotkova is the family name of Kira Muratova, the acclaimed Soviet and Ukrainian film director and screenwriter.
  • B. Tarasova
    Tarasova is a Russian surname most prominently associated with Tatiana Tarasova, a renowned figure skating coach and former competitor.
  • C. Nikolayeva
    Nikolayeva is a Russian surname most notably associated with the acclaimed Soviet pianist and composer Tatiana Nikolayeva.
  • D. Kuntsevskaya
    Kuntsevskaya is a Moscow Metro station on the Big Circle Line serving the Kuntsevo District in western Moscow.
  • E. Kastrychnitskaya
    Kastrychnitskaya is a central Minsk Metro station known for serving the heart of Belarus’s capital near key administrative and cultural landmarks.
  • 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: Korcheva
Triple: [Korchevskoy Uyezd, capital, Korcheva]
Generated description
Korcheva was a historical town in the Tver region of Russia that served as an administrative center before being submerged by the Ivankovo Reservoir in the 1930s.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Korcheva
Target entity description: Korcheva was a historical town in the Tver region of Russia that served as an administrative center before being submerged by the Ivankovo Reservoir in the 1930s.
  • A. Korotkova
    Korotkova is the family name of Kira Muratova, the acclaimed Soviet and Ukrainian film director and screenwriter.
  • B. Tarasova
    Tarasova is a Russian surname most prominently associated with Tatiana Tarasova, a renowned figure skating coach and former competitor.
  • C. Nikolayeva
    Nikolayeva is a Russian surname most notably associated with the acclaimed Soviet pianist and composer Tatiana Nikolayeva.
  • D. Kuntsevskaya
    Kuntsevskaya is a Moscow Metro station on the Big Circle Line serving the Kuntsevo District in western Moscow.
  • E. Kastrychnitskaya
    Kastrychnitskaya is a central Minsk Metro station known for serving the heart of Belarus’s capital near key administrative and cultural landmarks.
  • 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_69d7bdf1426c8190a4402e1c4cdec33a completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d964172490819080cd022ff8290b6e completed April 10, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69f684e7dec08190b522a8f3bfde6fe2 completed May 2, 2026, 11:12 p.m.
NEDg Description generation batch_69f685dac5cc8190b4bc2d81186c9266 completed May 2, 2026, 11:16 p.m.
NED2 Entity disambiguation (via description) batch_69f6869156048190b548ecd04561deb8 completed May 2, 2026, 11:19 p.m.
Created at: April 9, 2026, 5:25 p.m.