Triple

T38157417
Position Surface form Disambiguated ID Type / Status
Subject მიხეილ სააკაშვილი E952922 entity
Predicate იმყოფებოდა P190162 FINISHED
Object საქართველოს ციხეში 2020-იან წლებში 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 ციხეში 2020-იან წლებში | Statement: [მიხეილ სააკაშვილი, იმყოფებოდა, საქართველოს ციხეში 2020-იან წლებში]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: იმყოფებოდა
Context triple: [მიხეილ სააკაშვილი, იმყოფებოდა, საქართველოს ციხეში 2020-იან წლებში]
  • A. podlegała
    Indicates that one entity was subordinate to, under the authority of, or subject to the control or jurisdiction of another entity in the past.
  • B. dissolved
    Indicates that one substance has been mixed into another so thoroughly that it forms a uniform solution and is no longer distinguishable as a separate phase.
  • C. fell
    Indicates that an entity moved downward from a higher position to a lower one, typically due to gravity, often unintentionally or uncontrollably.
  • D. posedIn
    Indicates that an entity assumed a particular physical position or posture, typically for the purpose of being observed, photographed, drawn, or otherwise depicted.
  • E. impregnatedBy
    Indicates that one entity has caused another entity to become pregnant.
  • 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_69f76f0b93c48190a117319ab3a9f282 completed May 3, 2026, 3:51 p.m.
NER Named-entity recognition batch_69fcb089a8f881909aa9e722babd43f7 completed May 7, 2026, 3:32 p.m.
PD Predicate disambiguation batch_69fc45666c5c8190913bd632ac0e5b84 completed May 7, 2026, 7:55 a.m.
PDg Predicate description generation batch_69fcb088aac481909db90804faff315f completed May 7, 2026, 3:32 p.m.
Created at: May 3, 2026, 4:21 p.m.