Triple
T12725540
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tema |
E304094
|
entity |
| Predicate | languageUsed |
P238
|
FINISHED |
| Object | Twi |
E622267
|
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: Twi | Statement: [Tema, languageUsed, Twi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Twi Context triple: [Tema, languageUsed, Twi]
-
A.
Twi
Twi is a major Akan language spoken primarily in Ghana, known for its significant cultural influence and role in the West African diaspora.
-
B.
Twi language
chosen
Twi is a major Akan language spoken primarily in Ghana, serving as a widely used lingua franca in the country.
-
C.
Arebhashe
Arebhashe is a Dravidian language variety spoken primarily by Gowda communities in parts of Karnataka and Kerala in southwestern India.
-
D.
Kwéyòl
Kwéyòl is a French-based Creole language spoken primarily in the Lesser Antilles, notably in Saint Lucia and Dominica.
-
E.
Winaray
Winaray is an Austronesian language spoken primarily in the Eastern Visayas region of the Philippines, particularly in Samar, northern Leyte, and nearby areas.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96415ebe48190ae935bc3a9b00f65 |
completed | April 10, 2026, 8:56 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f67c85c6b88190bbdd94a43915a7a4 |
completed | May 2, 2026, 10:36 p.m. |
Created at: April 9, 2026, 5:25 p.m.