Triple

T30435894
Position Surface form Disambiguated ID Type / Status
Subject Politics of Georgia E774308 entity
Predicate hasBreakawayRegion P179239 FINISHED
Object Abkhazia NE NERFINISHED

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: Abkhazia | Statement: [Politics of Georgia, hasBreakawayRegion, Abkhazia]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: hasBreakawayRegion
Context triple: [Politics of Georgia, hasBreakawayRegion, Abkhazia]
  • A. hasRegion
    Indicates that an entity includes, contains, or is associated with a specific geographic or administrative region as part of its scope or structure.
  • B. hasRegionBehind
    Indicates that one region is spatially located behind another region relative to a given viewpoint or reference frame.
  • C. hasBroadRegion
    Indicates that an entity is associated with, located in, or applicable to a relatively large or general geographic or conceptual region.
  • D. hasBaseRegion
    Indicates that one entity is situated upon, supported by, or primarily associated with a specific underlying region or area.
  • E. hasAntipodalRegion
    Indicates that one region is located at the antipodal position of another region on a sphere, such that each point in one region corresponds to a point directly opposite it in the other.
  • F. None of above. chosen

Provenance (4 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_69f22492d2a88190995ce8745d9becaa completed April 29, 2026, 3:32 p.m.
NER Named-entity recognition batch_69f7201e241c819092d56a7bb99dc94d completed May 3, 2026, 10:14 a.m.
PD Predicate disambiguation batch_69f71cc405c08190863565609a4c8499 completed May 3, 2026, 10 a.m.
PDg Predicate description generation batch_69f71f8df5d48190944fbfbd9d573868 completed May 3, 2026, 10:12 a.m.
Created at: April 29, 2026, 8:07 p.m.