Triple
T11856794
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | West Central Sudanic languages |
E282059
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Fer language |
E904335
|
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: Fer language | Statement: [West Central Sudanic languages, hasMember, Fer language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fer language Context triple: [West Central Sudanic languages, hasMember, Fer language]
-
A.
Fer language
chosen
Fer language is a Central Sudanic language spoken by the Fer people of the Central African Republic and surrounding regions.
-
B.
Fang language
Fang is a Bantu language spoken primarily by the Fang people of Equatorial Guinea, Gabon, and Cameroon, notable for its significant influence on local varieties of Spanish and French.
-
C.
Phong language
The Phong language is a lesser-known Vietic language spoken by an ethnic minority community in Laos.
-
D.
Farefare language
The Farefare language is a Gur language spoken primarily in northern Ghana and southern Burkina Faso by the Frafra people.
-
E.
Mara language
The Mara language is a Kuki-Chin language spoken primarily by the Mara people in parts of northeastern India and western Myanmar.
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a699089c8190b7a298baf13dcded |
completed | April 10, 2026, 7:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f167d9b9e8819093582637941fc5ca |
completed | April 29, 2026, 2:07 a.m. |
Created at: April 8, 2026, 9:43 p.m.