Triple

T18181627
Position Surface form Disambiguated ID Type / Status
Subject Deve Bair Pass E435298 entity
Predicate hasRoadConnection P385 FINISHED
Object Kyustendil 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: Kyustendil | Statement: [Deve Bair Pass, hasRoadConnection, Kyustendil]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kyustendil
Context triple: [Deve Bair Pass, hasRoadConnection, Kyustendil]
  • A. Kyustendil chosen
    Kyustendil is a historic town and spa resort in western Bulgaria, known for its mineral springs, Roman and medieval heritage, and proximity to the Osogovo Mountains.
  • B. Vratsa
    Vratsa is a city in northwestern Bulgaria known as an industrial and cultural center near the Balkan Mountains.
  • C. Dobrinishte
    Dobrinishte is a small Bulgarian mountain town and spa resort in the Pirin Mountains, known for its mineral springs and as a gateway to hiking and skiing areas.
  • D. Butovo
    Butovo is a residential district in the southern part of Moscow, Russia, known for its large housing estates and rapid post-Soviet urban development.
  • E. Blagoevgrad
    Blagoevgrad is a city in southwestern Bulgaria known as a regional cultural and educational center, home to several universities and a vibrant student population.
  • 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_69d8b90c7ec081909b4694ccecb449c6 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4dffb3bc88190a627be9c444d5c7d completed April 19, 2026, 2 p.m.
Created at: April 10, 2026, 10:31 a.m.