Triple

T13223917
Position Surface form Disambiguated ID Type / Status
Subject Istriot E314824 entity
Predicate hasDialects P4251 FINISHED
Object Vodnjese
Vodnjese is a local dialect of the Istriot language traditionally spoken in and around the town of Vodnjan in Istria.
 E1029089 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: Vodnjese | Statement: [Istriot, hasDialects, Vodnjese]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vodnjese
Context triple: [Istriot, hasDialects, Vodnjese]
  • A. Dravinja
    Dravinja is a river in northeastern Slovenia that flows through the Dravinja Valley before joining the Drava River.
  • B. Vukosava
    Vukosava is known in Serbian medieval history as the mother of Saint Prince Lazar, the revered ruler and martyr of the Battle of Kosovo.
  • C. Vrbas
    Vrbas is a river in western Bosnia and Herzegovina that flows through cities like Banja Luka before joining the Sava River.
  • D. Vrbas
    Vrbas is a town and municipality in the Bačka region of northern Serbia, known as a local administrative, industrial, and transportation center.
  • E. Kosava
    Kosava is a small town in western Belarus known for its historic castle and as the birthplace region of Polish national hero Tadeusz Kościuszko.
  • 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: Vodnjese
Triple: [Istriot, hasDialects, Vodnjese]
Generated description
Vodnjese is a local dialect of the Istriot language traditionally spoken in and around the town of Vodnjan in Istria.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vodnjese
Target entity description: Vodnjese is a local dialect of the Istriot language traditionally spoken in and around the town of Vodnjan in Istria.
  • A. Dravinja
    Dravinja is a river in northeastern Slovenia that flows through the Dravinja Valley before joining the Drava River.
  • B. Vukosava
    Vukosava is known in Serbian medieval history as the mother of Saint Prince Lazar, the revered ruler and martyr of the Battle of Kosovo.
  • C. Vrbas
    Vrbas is a river in western Bosnia and Herzegovina that flows through cities like Banja Luka before joining the Sava River.
  • D. Vrbas
    Vrbas is a town and municipality in the Bačka region of northern Serbia, known as a local administrative, industrial, and transportation center.
  • E. Kosava
    Kosava is a small town in western Belarus known for its historic castle and as the birthplace region of Polish national hero Tadeusz Kościuszko.
  • 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_69d806affc688190a25b6ccc588e9c72 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf74d708190a61d8ad938653b06 completed April 10, 2026, 11:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6ff28612c81909d4fe93b0e571deb completed May 3, 2026, 7:54 a.m.
NEDg Description generation batch_69f702263edc8190ad775eb876837296 completed May 3, 2026, 8:07 a.m.
NED2 Entity disambiguation (via description) batch_69f7031d168881909b4320ea77ec211f completed May 3, 2026, 8:11 a.m.
Created at: April 9, 2026, 9:19 p.m.