Triple

T4815723
Position Surface form Disambiguated ID Type / Status
Subject Samtskhe E107582 entity
Predicate containsMonastery P20652 FINISHED
Object Vardzia E100994 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: Vardzia | Statement: [Samtskhe, containsMonastery, Vardzia]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vardzia
Context triple: [Samtskhe, containsMonastery, Vardzia]
  • A. Vardzia chosen
    Vardzia is a medieval cave monastery complex in southern Georgia, renowned for its extensive rock-cut dwellings and frescoed church.
  • B. Varniai
    Varniai is a historic town in Lithuania that once served as a key political and religious center of the Samogitian region.
  • C. Skvyra
    Skvyra is a town in central Ukraine historically known for its significant Jewish community and cultural life in the 19th and early 20th centuries.
  • D. Virvyčia
    Virvyčia is a river in northwestern Lithuania that serves as one of the tributaries feeding into the Venta River.
  • E. Pamūšis
    Pamūšis is a small settlement in present-day Lithuania, historically notable as the birthplace of Russian field marshal Mikhail Barclay de Tolly.
  • 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_69bd43f9efa081908314cb3e94fa1695 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6c8230888190a676695e51cb3ea4 completed March 20, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4db5652081909af5ef92df72c221 completed March 21, 2026, 7:50 a.m.
Created at: March 20, 2026, 1:23 p.m.