Triple

T17755911
Position Surface form Disambiguated ID Type / Status
Subject Savica River E443237 entity
Predicate hasNameInLanguage P15 FINISHED
Object Savica NE NERFINISHED

How this triple was built (2 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: Savica | Statement: [Savica River, hasNameInLanguage, Savica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Savica
Context triple: [Savica River, hasNameInLanguage, Savica]
  • A. Savica chosen
    Savica is a short but iconic karst river in northwestern Slovenia, best known for emerging from a cave and feeding the famous Savica Waterfall before flowing into Lake Bohinj.
  • B. Vrbas
    Vrbas is a town and municipality in the Bačka region of northern Serbia, known as a local administrative, industrial, and transportation center.
  • C. Vrbas
    Vrbas is a river in western Bosnia and Herzegovina that flows through cities like Banja Luka before joining the Sava River.
  • D. Drenica
    Drenica is a region in central Kosovo known as a stronghold of Albanian resistance and a focal point of conflict during the Kosovo War.
  • E. Zlatitsa
    Zlatitsa is a small historic town in western Bulgaria, situated in a valley of the Balkan Mountains and known for its mining and metallurgical industries.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9edf16c8190a59ebd245d378f4f completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4841e7050819083a4e638ca7484f7 completed April 19, 2026, 7:28 a.m.
Created at: April 10, 2026, 10:10 a.m.