Triple

T20672965
Position Surface form Disambiguated ID Type / Status
Subject Slovenian road network E508078 entity
Predicate connectsCity P4245 FINISHED
Object Maribor 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: Maribor | Statement: [Slovenian road network, connectsCity, Maribor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maribor
Context triple: [Slovenian road network, connectsCity, Maribor]
  • A. Maribor chosen
    Maribor is Slovenia’s second-largest city, known for its historic old town, wine culture, and the world’s oldest grapevine.
  • B. Celje
    Celje is a historic city in eastern Slovenia known for its medieval castle and former prominence as a regional political and economic center.
  • C. Ljubljana
    Ljubljana is the capital and largest city of Slovenia, known for its picturesque old town, Baroque and Art Nouveau architecture, and vibrant cultural scene along the Ljubljanica River.
  • D. Kranj
    Kranj is a historic industrial city in northwestern Slovenia, known as a regional economic center and gateway to the Slovenian Alps.
  • E. Šempeter pri Gorici
    Šempeter pri Gorici is a small town in western Slovenia near the Italian border, known for its close ties to the city of Nova Gorica and the cross-border Gorizia region.
  • 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_69e0b4c1164881909a3bf1e3ddb2bc32 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6b5cb1fc88190805f623e93a70368 completed April 20, 2026, 11:24 p.m.
Created at: April 16, 2026, 11:44 a.m.