Triple
T21645774
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lomé (district of Bè-Kpota) |
E534208
|
entity |
| Predicate | languageUsed |
P238
|
FINISHED |
| Object | Ewe |
—
|
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: Ewe | Statement: [Lomé (district of Bè-Kpota), languageUsed, Ewe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ewe Context triple: [Lomé (district of Bè-Kpota), languageUsed, Ewe]
-
A.
Ewe
chosen
Ewe is a major Niger–Congo language spoken primarily in southeastern Ghana and southern Togo by the Ewe people.
-
B.
Mòoré
Mòoré is a major Gur language spoken primarily by the Mossi people in Burkina Faso and surrounding West African countries.
-
C.
Ewenke
Ewenke is an alternative name for the Evenki language, a Tungusic language spoken by the Evenki people of Siberia and parts of China and Mongolia.
-
D.
Fante people
The Fante people are a major Akan ethnic group from Ghana’s coastal region, known for their historic trading states, rich cultural traditions, and significant influence in Ghanaian politics and education.
-
E.
Akposso people
The Akposso people are an ethnic group of Togo (and neighboring areas) known for their distinct cultural traditions and use of the Ikposo language.
- 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_69e0c466aec88190ba39c7543dbc8ba2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69ef5394c570819081dbbe7e0f98f7d3 |
completed | April 27, 2026, 12:16 p.m. |
Created at: April 16, 2026, 6:35 p.m.