Triple
T6922382
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zarma language |
E160218
|
entity |
| Predicate | closelyRelatedTo |
P37
|
FINISHED |
| Object | Songhay language |
E29015
|
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: Songhay language | Statement: [Zarma language, closelyRelatedTo, Songhay language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Songhay language Context triple: [Zarma language, closelyRelatedTo, Songhay language]
-
A.
Songhay languages
chosen
The Songhay languages are a group of closely related Nilo-Saharan languages spoken primarily along the Niger River in Mali, Niger, and neighboring West African countries.
-
B.
Yemba language
Yemba language is a major Bantu-related Grassfields language spoken primarily by the Bamileke people in western Cameroon.
-
C.
Bamileke languages
The Bamileke languages are a group of closely related Grassfields Bantu languages spoken primarily by the Bamileke people in western Cameroon.
-
D.
Banda-Ndélé language
The Banda-Ndélé language is a Central Sudanic language spoken by the Banda people, primarily in the Central African Republic.
-
E.
Sateré-Mawé language
The Sateré-Mawé language is an indigenous Tupian language spoken by the Sateré-Mawé people of the Brazilian Amazon.
- 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_69c6884d350081908d8a970e4d40ad78 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9fd159c819092a69d1a24e22dd5 |
completed | March 27, 2026, 7:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c761800804819082320a03f035f05b |
completed | March 28, 2026, 5:05 a.m. |
Created at: March 27, 2026, 2:26 p.m.