Triple
T22063200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ese Ejja people |
E545202
|
entity |
| Predicate | language |
P15
|
FINISHED |
| Object | Ese Ejja language |
—
|
NE NERFINISHED |
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: Ese Ejja language | Statement: [Ese Ejja people, language, Ese Ejja language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ese Ejja language Context triple: [Ese Ejja people, language, Ese Ejja language]
-
A.
Ese Ejja language
chosen
The Ese Ejja language is an indigenous Tacanan language spoken by the Ese Ejja people in parts of Bolivia and Peru.
-
B.
Ezha language
The Ezha language is an Afroasiatic Semitic language spoken by the Ezha people of Ethiopia as part of the Gurage linguistic group.
-
C.
Ijesha language
The Ijesha language is a regional variety of Yoruba spoken primarily by the Ijesha people in southwestern Nigeria.
-
D.
Jahai language
The Jahai language is an indigenous Mon–Khmer language spoken by the Jahai people, a small hunter-gatherer community in the Malay Peninsula.
-
E.
Aja language
The Aja language is a Gbe language of the Niger-Congo family spoken primarily in parts of Benin and Togo.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e3377c48190890c17407b9527d6 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f12881f9e0819091b8e6d8ff6802bd |
completed | April 28, 2026, 9:37 p.m. |
Created at: April 16, 2026, 8:27 p.m.