Triple

T316083
Position Surface form Disambiguated ID Type / Status
Subject Kartvelebi E7709 entity
Predicate hasWritingSystem P454 FINISHED
Object Georgian script 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: Georgian script | Statement: [Kartvelebi, hasWritingSystem, Georgian script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgian script
Context triple: [Kartvelebi, hasWritingSystem, Georgian script]
  • A. Georgian script chosen
    The Georgian script is the unique alphabetic writing system used to write the Georgian language and several related Kartvelian languages.
  • B. Cyrillic script
    The Cyrillic script is an alphabetic writing system used for many Slavic and other Eurasian languages, including Russian, Bulgarian, Serbian, and Ukrainian.
  • C. Glagolitic script
    Glagolitic script is the oldest known Slavic alphabet, created in the 9th century by Saints Cyril and Methodius for the translation of Christian texts into Old Church Slavonic.
  • D. Georgian language
    The Georgian language is a Kartvelian language spoken primarily in the country of Georgia, known for its unique Mkhedruli script and rich literary tradition.
  • E. Ruqʿah script
    Ruqʿah script is a simple, highly legible Arabic handwriting style commonly used for everyday writing and official documents in the Arab world.
  • 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_69a2e7e7af7881908890039d6be4e9b8 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ea6462148190825acc57f6d2adaf completed Feb. 28, 2026, 1:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3cafef7d48190b00f577488298605 completed March 1, 2026, 5:13 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.