Triple

T12034077
Position Surface form Disambiguated ID Type / Status
Subject Imereti E286488 entity
Predicate containsCity P294 FINISHED
Object Kobuleti E109179 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: Kobuleti | Statement: [Imereti, containsCity, Kobuleti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kobuleti
Context triple: [Imereti, containsCity, Kobuleti]
  • A. Kobuleti chosen
    Kobuleti is a Georgian Black Sea resort town known for its long pebble beaches and role as a popular holiday destination in the autonomous region of Adjara.
  • B. Kardenakhi
    Kardenakhi is a Georgian village in the Kakheti region renowned for producing high-quality wines under its own appellation.
  • C. Goubuli
    Goubuli is a famous Chinese food brand best known for its traditional Tianjin-style stuffed buns (baozi) with a long history and strong cultural recognition.
  • D. Balka
    Balka is a coastal village and beach area on the Danish island of Bornholm, known for its shallow, child-friendly sandy shoreline and holiday atmosphere.
  • E. Gevaş
    Gevaş is a town and district in eastern Turkey, situated on the southern shore of Lake Van in Van Province.
  • 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_69d6ab4669e48190b59246358b0383ab completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d9040724ec8190808f334013ddc6d6 completed April 10, 2026, 2:07 p.m.
NED1 Entity disambiguation (via context triple) batch_69f49d6ec4b8819093ff50254a851444 completed May 1, 2026, 12:32 p.m.
Created at: April 8, 2026, 9:47 p.m.