Triple

T16442669
Position Surface form Disambiguated ID Type / Status
Subject Sava Bohinjka E399342 entity
Predicate mouthLocation P417 FINISHED
Object Radovljica E1065086 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: Radovljica | Statement: [Sava Bohinjka, mouthLocation, Radovljica]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Radovljica
Context triple: [Sava Bohinjka, mouthLocation, Radovljica]
  • A. Radovljica chosen
    Radovljica is a historic town in northwestern Slovenia known for its well-preserved medieval old town and cultural heritage.
  • B. Grožnjan
    Grožnjan is a small medieval hilltop town in Istria, Croatia, renowned as an artists’ colony and cultural center.
  • C. Šentjur
    Šentjur is a Slovenian basketball club competing in the country’s top professional league.
  • D. Vodnjan
    Vodnjan is a historic town in southwestern Croatia’s Istria region, known for its multicultural heritage, medieval architecture, and preservation of local Romance dialects.
  • E. Škofja Loka
    Škofja Loka is a historic medieval town in northwestern Slovenia, known for its well-preserved old town, castle, and rich cultural heritage.
  • 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_69d87f2c6778819080fcfae53be8f12a completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e32cd8d2988190acb5722a15623319 completed April 18, 2026, 7:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a005815efc48190868305f428cb9085 completed May 10, 2026, 10:04 a.m.
Created at: April 10, 2026, 5:10 a.m.