Triple

T17242780
Position Surface form Disambiguated ID Type / Status
Subject Orašac E418543 entity
Predicate locatedIn P40 FINISHED
Object Šumadija region 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: Šumadija region | Statement: [Orašac, locatedIn, Šumadija region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Šumadija region
Context triple: [Orašac, locatedIn, Šumadija region]
  • A. Šumadija region chosen
    The Šumadija region is a historic and central area of Serbia characterized by rolling hills, fertile land, and a strong role in the country’s cultural and political development.
  • B. Mačva region
    The Mačva region is a historical and geographical area in western Serbia, known for its fertile plains, agriculture, and cultural centers such as the city of Šabac.
  • C. Raška region
    The Raška region is a historic area of central Serbia considered the cradle of the medieval Serbian state and the Serbian Orthodox Church.
  • D. Bijeljina region
    The Bijeljina region is an area in northeastern Bosnia and Herzegovina known for its agricultural plains and as part of the historical region of Semberija.
  • E. Posavina region
    The Posavina region is a geographical area along the Sava River in Southeast Europe, spanning parts of several countries and known for its fertile plains and riverine landscapes.
  • 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_69d886d8e96081909870bff6c3d0bf09 completed April 10, 2026, 5:12 a.m.
NER Named-entity recognition batch_69e42e21003c81908c884a3c8712676a completed April 19, 2026, 1:21 a.m.
Created at: April 10, 2026, 5:39 a.m.