Triple

T3424652
Position Surface form Disambiguated ID Type / Status
Subject Transylvania E72198 entity
Predicate borders P224 FINISHED
Object Maramureș E139724 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: Maramureș | Statement: [Transylvania, borders, Maramureș]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maramureș
Context triple: [Transylvania, borders, Maramureș]
  • A. Maramureș region chosen
    The Maramureș region is a historic area in northern Romania renowned for its well-preserved rural traditions, wooden churches, and distinctive folk culture.
  • B. Satu Mare
    Satu Mare is a city in northwestern Romania near the Hungarian border, known as a regional economic and cultural center with a diverse ethnic heritage.
  • C. Crișana
    Crișana is a historical region in western Romania, known for its multicultural heritage and location between the Apuseni Mountains and the Hungarian border.
  • D. Mediaș
    Mediaș is a historic town in central Romania’s Transylvania region, known for its well-preserved medieval architecture and long-standing Transylvanian Saxon heritage.
  • E. Mureș County
    Mureș County is an administrative region in central Romania, known for its multicultural population, historic cities like Târgu Mureș, and its location in the heart of Transylvania.
  • 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_69ad85ae14308190bcbc25cfa0246c0b completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb97fa2d88190a79cb8c7be4b3696 completed March 8, 2026, 6:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69b38bb30b708190ab06280feea59eaf completed March 13, 2026, 3:59 a.m.
Created at: March 8, 2026, 3:15 p.m.