Triple

T9685728
Position Surface form Disambiguated ID Type / Status
Subject Bodrog E234401 entity
Predicate region P40 FINISHED
Object Zemplín E278195 NE 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: Zemplín | Statement: [Bodrog, region, Zemplín]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Zemplín
Context triple: [Bodrog, region, Zemplín]
  • A. Zemplín chosen
    Zemplín is a historical and geographical region in eastern Slovakia known for its wine production, cultural heritage, and proximity to the borders with Hungary and Ukraine.
  • B. Kysuce
    Kysuce is a mountainous region in northwestern Slovakia known for its forests, traditional villages, and proximity to the Czech and Polish borders.
  • C. Terchová
    Terchová is a Slovak village in the Malá Fatra mountains known as the birthplace of the legendary outlaw Juraj Jánošík and for its rich folk traditions and natural scenery.
  • D. Svitava
    Svitava is a river in the Czech Republic that flows through the city of Brno and is one of its main waterways.
  • E. Vodňany
    Vodňany is a small historic town in the South Bohemian Region of the Czech Republic, known for its traditional fishpond farming and picturesque rural character.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69ca84ca73208190957a900c8543bdcc completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9cd0877c81909fde1989d946aae9 completed April 1, 2026, 10:31 p.m.
NED1 Entity disambiguation (via context triple) batch_69d19f76aca481909692b29cac3c3dc3 completed April 4, 2026, 11:32 p.m.
Created at: March 30, 2026, 8:16 p.m.