Triple
T7273971
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dioula |
E162977
|
entity |
| Predicate | writingSystem |
P454
|
FINISHED |
| Object | N’Ko script |
E150322
|
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: N’Ko script | Statement: [Dioula, writingSystem, N’Ko script]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: N’Ko script Context triple: [Dioula, writingSystem, N’Ko script]
-
A.
N'Ko script
chosen
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.
-
B.
Tifinagh
Tifinagh is an ancient and modern script used primarily to write Berber (Amazigh) languages across North Africa.
-
C.
Tirhuta script
Tirhuta script is a traditional Brahmic writing system historically used for the Maithili language of the Mithila region in India and Nepal.
-
D.
Adlam script
The Adlam script is an alphabetic writing system created in the late 20th century to represent the Fulani (Fulfulde) language and promote literacy among its speakers in West Africa.
-
E.
Khojki script
The Khojki script is a historical writing system used primarily by the Nizari Ismaili community of South Asia to record religious and literary texts in languages such as Sindhi and Gujarati.
- 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb0de9f48190807dd148758bad62 |
completed | March 27, 2026, 8:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db2936dc8190aed38888bb5e47b8 |
completed | March 28, 2026, 1:44 p.m. |
Created at: March 27, 2026, 2:58 p.m.