Triple

T11578432
Position Surface form Disambiguated ID Type / Status
Subject Dogon languages E274563 entity
Predicate hasWritingSystem P454 FINISHED
Object Ajami script E222793 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: Ajami script | Statement: [Dogon languages, hasWritingSystem, Ajami script]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ajami script
Context triple: [Dogon languages, hasWritingSystem, Ajami script]
  • A. Ajami script chosen
    Ajami script is a modified form of the Arabic script historically used to write various African languages such as Hausa, Fulani, and Wolof.
  • B. Ruqʿah script
    Ruqʿah script is a simple, highly legible Arabic handwriting style commonly used for everyday writing and official documents in the Arab world.
  • C. Nuskhuri script
    The Nuskhuri script is a medieval ecclesiastical form of the Georgian alphabet used primarily in religious manuscripts and liturgical texts.
  • D. Takri script
    The Takri script is an abugida historically used in the western Himalayas, particularly in regions of present-day Himachal Pradesh and Jammu, to write several Indo-Aryan languages such as Dogri and Jaunsari.
  • E. Diwani script
    Diwani script is an ornate Ottoman-era style of Arabic calligraphy characterized by its intricate, flowing lines and dense, decorative composition often used in royal decrees and official documents.
  • 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_69d6aae5ac3c81908d2b0a3a665665b2 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8904b46288190890ecafd6ceb0c3d completed April 10, 2026, 5:53 a.m.
NED1 Entity disambiguation (via context triple) batch_69e714080a60819095205355776c8637 completed April 21, 2026, 6:07 a.m.
Created at: April 8, 2026, 9:38 p.m.