Triple

T24909960
Position Surface form Disambiguated ID Type / Status
Subject Шешупе E623818 entity
Predicate крупныйПриток P157866 FINISHED
Object Виштитис
Виштитис — озеро на границе Литвы и России (Калининградской области), известное как исток реки Шешупе и часть охраняемой природной территории.
 E1655842 NE FINISHED

How this triple was built (3 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: Виштитис | Statement: [Шешупе, крупныйПриток, Виштитис]
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: Виштитис
Triple: [Шешупе, крупныйПриток, Виштитис]
Generated description
Виштитис — озеро на границе Литвы и России (Калининградской области), известное как исток реки Шешупе и часть охраняемой природной территории.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: крупныйПриток
Context triple: [Шешупе, крупныйПриток, Виштитис]
  • A. впадаетВБолееКрупнуюРеку chosen
    Indicates that a smaller river flows into and joins a larger river.
  • B. isMajorWatercourseOf
    Indicates that a watercourse is a primary or significant river or stream associated with, or flowing through, a particular geographic area or feature.
  • C. тип реки
    Indicates the classification or category of a river based on its characteristics or role.
  • D. tributary
    Indicates that one watercourse flows into and feeds another, contributing its water to a larger stream, river, or lake.
  • E. largestInflowRiver
    Indicates that one river has the greatest volume of water flowing into a specified body (such as a lake, sea, or another river) compared to all other contributing rivers.
  • F. None of above.

Provenance (6 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_69e2fac889c081908e9ff686cb428e5a completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f464b4c9b0819085daa00c7c3b8b76 completed May 1, 2026, 8:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a103329f5608190b26d4489ea3a34a2 completed May 22, 2026, 10:42 a.m.
NEDg Description generation batch_6a1033edb6848190b35070d8784af90e completed May 22, 2026, 10:46 a.m.
NED2 Entity disambiguation (via description) batch_6a10348fb55c819087a28d4a7280589c completed May 22, 2026, 10:48 a.m.
PD Predicate disambiguation batch_69f45cf017a88190b4985b11159c907d completed May 1, 2026, 7:57 a.m.
Created at: April 18, 2026, 5:27 a.m.