Triple

T19807359
Position Surface form Disambiguated ID Type / Status
Subject Syas River E475847 entity
Predicate hasRussianName P20560 FINISHED
Object Сясь
Сясь — река на северо-западе России, протекающая по Ленинградской области и впадающая в Ладожское озеро.
 E1395486 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: Сясь | Statement: [Syas River, hasRussianName, Сясь]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Сясь
Context triple: [Syas River, hasRussianName, Сясь]
  • A. Sussala
    Sussala was a medieval ruler of Kashmir from the Lohara dynasty, known for his turbulent reign marked by internal conflicts and efforts to consolidate royal authority.
  • B. Бесы
    «Бесы» — это роман Фёдора Достоевского, политико-философская драма о разрушительном влиянии радикальных идей на людей и общество в России XIX века.
  • C. Seisia
    Seisia is a small coastal community in far northern Queensland, Australia, known as a key Torres Strait transport and fishing hub near the tip of Cape York Peninsula.
  • D. Sapochnik
    Sapochnik is the surname of Miguel Sapochnik, a British film and television director known for his work on series such as Game of Thrones.
  • E. Siekopai
    The Siekopai are an Indigenous people of the western Amazon, primarily living in Ecuador and Peru, known for their rich shamanic traditions and deep ecological knowledge of the rainforest.
  • 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: Сясь
Triple: [Syas River, hasRussianName, Сясь]
Generated description
Сясь — река на северо-западе России, протекающая по Ленинградской области и впадающая в Ладожское озеро.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Сясь
Target entity description: Сясь — река на северо-западе России, протекающая по Ленинградской области и впадающая в Ладожское озеро.
  • A. Sussala
    Sussala was a medieval ruler of Kashmir from the Lohara dynasty, known for his turbulent reign marked by internal conflicts and efforts to consolidate royal authority.
  • B. Бесы
    «Бесы» — это роман Фёдора Достоевского, политико-философская драма о разрушительном влиянии радикальных идей на людей и общество в России XIX века.
  • C. Seisia
    Seisia is a small coastal community in far northern Queensland, Australia, known as a key Torres Strait transport and fishing hub near the tip of Cape York Peninsula.
  • D. Sapochnik
    Sapochnik is the surname of Miguel Sapochnik, a British film and television director known for his work on series such as Game of Thrones.
  • E. Siekopai
    The Siekopai are an Indigenous people of the western Amazon, primarily living in Ecuador and Peru, known for their rich shamanic traditions and deep ecological knowledge of the rainforest.
  • 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_69d8e51bc4208190a1c57d8c5d1b15e4 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65428f5c48190be6ae0d6a77675d2 completed April 20, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07c50e7bbc81908808e8e734f6a360 completed May 16, 2026, 1:14 a.m.
NEDg Description generation batch_6a07c6c26e708190aeb42569dc5e107c completed May 16, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_6a07c7549de08190916e3e48125beebb completed May 16, 2026, 1:24 a.m.
Created at: April 10, 2026, 1:49 p.m.