Triple

T18392844
Position Surface form Disambiguated ID Type / Status
Subject Свирь E449779 entity
Predicate hasLeftTributary P415 FINISHED
Object Важинка
Важинка — небольшая река в Ленинградской области России, являющаяся притоком Свири и протекающая через лесисто-болотистые районы Карельского перешейка.
 E1322568 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: Важинка | Statement: [Свирь, hasLeftTributary, Важинка]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Важинка
Context triple: [Свирь, hasLeftTributary, Важинка]
  • A. Dorohozhychi
    Dorohozhychi is a station on the Kyiv Metro system in Ukraine.
  • B. Zvenyhorodka
    Zvenyhorodka is a town in central Ukraine that serves as a local administrative and cultural center within Cherkasy Oblast.
  • C. Zhmerynka
    Zhmerynka is a city in central Ukraine known as an important regional railway junction and administrative center.
  • D. Свислочь
    Свислочь — река в Беларуси, протекающая через Минск и являющаяся одним из заметных водных объектов столицы.
  • E. Vyazniki
    Vyazniki is a historic town in western Russia known for its traditional architecture and location on the Klyazma River.
  • 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: Важинка
Triple: [Свирь, hasLeftTributary, Важинка]
Generated description
Важинка — небольшая река в Ленинградской области России, являющаяся притоком Свири и протекающая через лесисто-болотистые районы Карельского перешейка.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Важинка
Target entity description: Важинка — небольшая река в Ленинградской области России, являющаяся притоком Свири и протекающая через лесисто-болотистые районы Карельского перешейка.
  • A. Dorohozhychi
    Dorohozhychi is a station on the Kyiv Metro system in Ukraine.
  • B. Zvenyhorodka
    Zvenyhorodka is a town in central Ukraine that serves as a local administrative and cultural center within Cherkasy Oblast.
  • C. Zhmerynka
    Zhmerynka is a city in central Ukraine known as an important regional railway junction and administrative center.
  • D. Свислочь
    Свислочь — река в Беларуси, протекающая через Минск и являющаяся одним из заметных водных объектов столицы.
  • E. Vyazniki
    Vyazniki is a historic town in western Russia known for its traditional architecture and location on the Klyazma River.
  • 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_69d8b9fab8a8819086a9ddc0871715e0 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e518435cf481908393c1eb2b4ba659 completed April 19, 2026, 6 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03e23eac3081909deb4a491da08bac completed May 13, 2026, 2:30 a.m.
NEDg Description generation batch_6a03e46859d481909c2738b6f47ea7b3 completed May 13, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_6a03e4b743688190a582fef43f7b1956 completed May 13, 2026, 2:40 a.m.
Created at: April 10, 2026, 10:46 a.m.