Triple

T24792326
Position Surface form Disambiguated ID Type / Status
Subject Миџор E620282 entity
Predicate налазиСеНаГраници P13760 FINISHED
Object граница Србије и Бугарске LITERAL FINISHED

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: граница Србије и Бугарске | Statement: [Миџор, налазиСеНаГраници, граница Србије и Бугарске]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: налазиСеНаГраници
Context triple: [Миџор, налазиСеНаГраници, граница Србије и Бугарске]
  • A. Bridges of Struga
    Indicates a relationship where bridges are located in, associated with, or spanning areas within Struga.
  • B. exploresBoundaryBetween
    Indicates a relationship in which one entity actively investigates, tests, or probes the limits or dividing line between two domains, states, or concepts.
  • C. borderStreet
    Indicates that a street forms or lies along the boundary between two geographic areas or properties.
  • D. Höhepunkt
    Indicates the climax or peak point reached within an event, process, or development.
  • E. crossesBorderOf chosen
    Indicates that one entity passes from one side of the boundary of another entity (typically a region or area) to the other side, traversing its border.
  • F. None of above.

Provenance (3 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_69e2fabe77c8819085f7ce6486248139 completed April 18, 2026, 3:30 a.m.
NER Named-entity recognition batch_69f4110424188190889a13976b16b18a completed May 1, 2026, 2:33 a.m.
PD Predicate disambiguation batch_69f40ef612c88190ab2f3f08d4a92018 completed May 1, 2026, 2:24 a.m.
Created at: April 18, 2026, 4:47 a.m.