Triple

T37788029
Position Surface form Disambiguated ID Type / Status
Subject მიხეილ მესხის სახელობის სტადიონი E942008 entity
Predicate ფუნქცია P81043 FINISHED
Object მრავალფუნქციური სპორტული არენა LITERAL 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: მრავალფუნქციური სპორტული არენა | Statement: [მიხეილ მესხის სახელობის სტადიონი, ფუნქცია, მრავალფუნქციური სპორტული არენა]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ფუნქცია
Context triple: [მიხეილ მესხის სახელობის სტადიონი, ფუნქცია, მრავალფუნქციური სპორტული არენა]
  • A. functie chosen
    Indicates that one entity serves as a function, role, or operational purpose in relation to another entity.
  • B. 기능
    Indicates that an entity has a particular function, role, or operational capability.
  • C. toolFunction
    Indicates that one entity serves as a tool used to perform a particular function or achieve a specific purpose for another entity.
  • D. formFunction
    Indicates that one entity’s physical form, structure, or configuration determines or enables the function or role performed by another (or by itself).
  • E. језикФункције
    Indicates that something is the programming or implementation language used for a given function.
  • F. None of above.

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_69f76ee5cb0c81909a363d1c929156c0 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fbb9e8108c8190ae1c7940b1677e95 completed May 6, 2026, 10 p.m.
PD Predicate disambiguation batch_69fbb141605c8190b9c27d70352522db completed May 6, 2026, 9:23 p.m.
Created at: May 3, 2026, 4:19 p.m.