Triple

T37836683
Position Surface form Disambiguated ID Type / Status
Subject ლევან კობიაშვილი E943355 entity
Predicate პოლიტიკური_აქტივობა P29201 FINISHED
Object საქართველოს პარლამენტის დეპუტატი 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: საქართველოს პარლამენტის დეპუტატი | Statement: [ლევან კობიაშვილი, პოლიტიკური_აქტივობა, საქართველოს პარლამენტის დეპუტატი]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: პოლიტიკური_აქტივობა
Context triple: [ლევან კობიაშვილი, პოლიტიკური_აქტივობა, საქართველოს პარლამენტის დეპუტატი]
  • A. postPoliticalActivity
    Indicates that an entity engages in political actions or activities following a particular event, period, or condition.
  • B. politicalAct chosen
    Indicates that an entity performs, participates in, or is involved with an action related to politics, governance, or public policy.
  • C. genreOfPoliticalActivity
    Indicates the specific type or category of political activity that characterizes or classifies a given political action or engagement.
  • D. oppositionActivity
    Indicates that one entity engages in actions or behaviors that resist, counter, or work against another entity, its goals, or its activities.
  • E. hasPoliticalActivityIn
    Indicates that an entity engages in or is associated with political activities within a specified location or jurisdiction.
  • 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_69f76eeb0f7081908d6d3adbc469889c completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fbbae559a8819086ef839973f8d9b2 completed May 6, 2026, 10:04 p.m.
PD Predicate disambiguation batch_69fbb1440fa08190abf25ba684f75b6e completed May 6, 2026, 9:23 p.m.
Created at: May 3, 2026, 4:19 p.m.