Triple

T20062587
Position Surface form Disambiguated ID Type / Status
Subject Kose Parish E499517 entity
Predicate containsSettlement P847 FINISHED
Object Viskla
Viskla is a small village located in Kose Parish in northern Estonia.
 E1408653 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: Viskla | Statement: [Kose Parish, containsSettlement, Viskla]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Viskla
Context triple: [Kose Parish, containsSettlement, Viskla]
  • A. Viskuli
    Viskuli is a government hunting lodge in the Białowieża Forest of Belarus, historically significant as the site where the leaders of Russia, Ukraine, and Belarus signed the Belavezha Accords dissolving the Soviet Union.
  • B. Niska
    Niska is a French rapper known for his energetic trap-influenced style, inventive slang, and hit tracks that have significantly impacted the Francophone hip-hop scene.
  • C. Niska
    Niska is an alternative name for the Nisga’a language, an Indigenous language spoken by the Nisga’a people of northwestern British Columbia, Canada.
  • D. Vawkavisk
    Vawkavisk is a town in western Belarus known for its long history dating back to medieval times and its role as a regional cultural and economic center.
  • E. Visy
    Visy is a major Australian packaging and recycling company known for manufacturing paper, cardboard, and related products while operating extensive recycling and waste recovery facilities.
  • 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: Viskla
Triple: [Kose Parish, containsSettlement, Viskla]
Generated description
Viskla is a small village located in Kose Parish in northern Estonia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Viskla
Target entity description: Viskla is a small village located in Kose Parish in northern Estonia.
  • A. Viskuli
    Viskuli is a government hunting lodge in the Białowieża Forest of Belarus, historically significant as the site where the leaders of Russia, Ukraine, and Belarus signed the Belavezha Accords dissolving the Soviet Union.
  • B. Niska
    Niska is a French rapper known for his energetic trap-influenced style, inventive slang, and hit tracks that have significantly impacted the Francophone hip-hop scene.
  • C. Niska
    Niska is an alternative name for the Nisga’a language, an Indigenous language spoken by the Nisga’a people of northwestern British Columbia, Canada.
  • D. Vawkavisk
    Vawkavisk is a town in western Belarus known for its long history dating back to medieval times and its role as a regional cultural and economic center.
  • E. Visy
    Visy is a major Australian packaging and recycling company known for manufacturing paper, cardboard, and related products while operating extensive recycling and waste recovery facilities.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66376f2d4819081b9e1b265650e5b completed April 20, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_6a081612662c81909cb1e90910ca76ac completed May 16, 2026, 7 a.m.
NEDg Description generation batch_6a0816d3c71081909138d3144a108266 completed May 16, 2026, 7:03 a.m.
NED2 Entity disambiguation (via description) batch_6a08179df70c81908ea5bc596a8ba756 completed May 16, 2026, 7:07 a.m.
Created at: April 11, 2026, 3:39 p.m.