Triple
T14399846
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Museum of Niger |
E357040
|
entity |
| Predicate | languageOfWorkOrName |
P15
|
FINISHED |
| Object | Zarma |
E160218
|
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: Zarma | Statement: [National Museum of Niger, languageOfWorkOrName, Zarma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Zarma Context triple: [National Museum of Niger, languageOfWorkOrName, Zarma]
-
A.
Zarma language
chosen
The Zarma language is a widely spoken Nilo-Saharan language of West Africa, primarily used in Niger and neighboring countries, and serves as a major lingua franca in the region.
-
B.
Guinean Fula
Guinean Fula is a regional variety of the Fula (Fulani) language spoken primarily in Guinea.
-
C.
Dioula
Dioula is a Mande language of West Africa, widely used as a trade and lingua franca language in countries like Burkina Faso, Côte d’Ivoire, and Mali.
-
D.
Casamance Mandinka
Casamance Mandinka is a regional variety of the Mandinka language spoken primarily in the Casamance area of southern Senegal.
-
E.
Bambara
Bambara is a major Mande language widely spoken in Mali and neighboring West African countries, serving as a key lingua franca in the region.
- 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_69d827927c988190ad98bb0360981783 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de9083f9d081908fe5c99655c410b3 |
completed | April 14, 2026, 7:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd5bc424f88190ab3a1c1aec61cb40 |
completed | May 8, 2026, 3:43 a.m. |
Created at: April 10, 2026, 1:17 a.m.