Triple

T86810
Position Surface form Disambiguated ID Type / Status
Subject Georgians E1745 entity
Predicate writingSystem P454 FINISHED
Object Mkhedruli E7247 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: Mkhedruli | Statement: [Georgians, writingSystem, Mkhedruli]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mkhedruli
Context triple: [Georgians, writingSystem, Mkhedruli]
  • A. Kato Svanidze
    Kato Svanidze was the first wife of Joseph Stalin, remembered primarily for her early death and its profound emotional impact on him.
  • B. Georgian script chosen
    The Georgian script is the unique alphabetic writing system used to write the Georgian language and several related Kartvelian languages.
  • C. Andrei
    Andrei is a masculine given name commonly used in Slavic and Eastern European countries, equivalent to the English name Andrew.
  • D. Theodor
    Theodor "Ted" Nelson is an American pioneer of information technology best known for coining the term "hypertext" and envisioning global hyperlinked document systems.
  • E. Aha Makhav
    Aha Makhav is the endonym used by the Mojave people to refer to themselves and their cultural identity.
  • 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_69a24c8150408190910a693eb51c1f71 completed Feb. 28, 2026, 2:01 a.m.
NER Named-entity recognition batch_69a24f50e004819083f5bfccd597a312 completed Feb. 28, 2026, 2:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69a26243abb881908e732c8f885cc694 completed Feb. 28, 2026, 3:34 a.m.
Created at: Feb. 28, 2026, 2:06 a.m.