Triple

T4106673
Position Surface form Disambiguated ID Type / Status
Subject Kote Marjanishvili E88467 entity
Predicate familyName P18 FINISHED
Object Marjanishvili E88467 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: Marjanishvili | Statement: [Kote Marjanishvili, familyName, Marjanishvili]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marjanishvili
Context triple: [Kote Marjanishvili, familyName, Marjanishvili]
  • A. Arsukidze
    Arsukidze was a medieval Georgian architect renowned as the master builder of the Svetitskhoveli Cathedral in Mtskheta.
  • B. Javakhishvili
    Javakhishvili is a Georgian surname most notably associated with prominent figures such as writer Mikheil Javakhishvili.
  • C. Robakidze
    Robakidze is a Georgian surname most notably borne by the writer and public figure Grigol Robakidze.
  • D. Mkhedruli
    Mkhedruli is the modern Georgian script used for writing the Georgian language and several related Kartvelian languages.
  • E. Kote Marjanishvili chosen
    Kote Marjanishvili was a prominent Georgian theater director and reformer, regarded as one of the founders of modern Georgian stage art.
  • 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_69aed9484fb881909146f4c772ad277c completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69af019c7a3c8190a503ce80e87dc3b3 completed March 9, 2026, 5:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5f5a4f75481909236504eaf81ce33 completed March 14, 2026, 11:56 p.m.
Created at: March 9, 2026, 3:40 p.m.