Triple

T19841696
Position Surface form Disambiguated ID Type / Status
Subject Lipany E476746 entity
Predicate regionType P1828 FINISHED
Object Šariš 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: Šariš | Statement: [Lipany, regionType, Šariš]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Šariš
Context triple: [Lipany, regionType, Šariš]
  • A. Šariš chosen
    Šariš is a historic region in northeastern Slovakia known for its medieval towns, folk traditions, and cultural heritage centered around the city of Prešov.
  • B. Galičnik
    Galičnik is a historic mountain village in North Macedonia, famed for its traditional architecture and the annual Galičnik Wedding Festival celebrating Macedonian customs and folklore.
  • C. Kamnik
    Kamnik is a historic town in northern Slovenia known for its medieval architecture, nearby Kamnik–Savinja Alps, and role as a regional cultural and tourist center.
  • D. Korošec
    Korošec is a Slovene surname most notably associated with Anton Korošec, a prominent early 20th-century Slovenian politician and statesman.
  • E. Trstenik
    Trstenik is a town in central Serbia known for its location along the West Morava River and its role as a local industrial and cultural center.
  • 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_69d8e51d39d081909bcfafeaaf3d2fcc completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e65806375c8190a4f45f14aeb06515 completed April 20, 2026, 4:44 p.m.
Created at: April 10, 2026, 1:51 p.m.