Triple

T1852841
Position Surface form Disambiguated ID Type / Status
Subject Kel Ajjer E41633 entity
Predicate usesScript P1587 FINISHED
Object Tifinagh E28394 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: Tifinagh | Statement: [Kel Ajjer, usesScript, Tifinagh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tifinagh
Context triple: [Kel Ajjer, usesScript, Tifinagh]
  • A. Tifinagh chosen
    Tifinagh is an ancient and modern script used primarily to write Berber (Amazigh) languages across North Africa.
  • B. Maghribi script
    Maghribi script is a distinctive, rounded style of Arabic calligraphy that developed in the Islamic West (North Africa and al-Andalus), characterized by its bold curves and unique regional letterforms.
  • C. N'Ko script
    N'Ko script is an indigenous alphabetic writing system created in 1949 by Solomana Kante for Manding languages of West Africa, such as Mandinka, Bambara, and Dyula.
  • D. Punic script
    Punic script is a later, regionally adapted form of the Phoenician writing system used primarily in Carthage and other Punic-speaking communities around the western Mediterranean.
  • 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_69a8864a83848190a4ec02721306c511 completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb06999f4819086386aafb789a368 completed March 7, 2026, 4:58 a.m.
NED1 Entity disambiguation (via context triple) batch_69adc9c81f2c81908339f6a1d1987631 completed March 8, 2026, 7:11 p.m.
Created at: March 4, 2026, 7:33 p.m.