Triple
T23449263
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brong-Ahafo Region |
E567728
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Techiman |
—
|
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: Techiman | Statement: [Brong-Ahafo Region, containsCity, Techiman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Techiman Context triple: [Brong-Ahafo Region, containsCity, Techiman]
-
A.
Techiman
chosen
Techiman is a prominent commercial and transportation hub in central Ghana, known especially for its large traditional market and role in regional trade.
-
B.
Tepiman
Tepiman is a subgroup of Uto-Aztecan languages spoken primarily in the southwestern United States and northern Mexico, including languages such as O'odham and Tepehuán.
-
C.
Simanu
Simanu is a month in the ancient Babylonian calendar, corresponding roughly to late spring or early summer in the modern Gregorian calendar.
-
D.
Danchimah
Danchimah is a surname of likely African origin, associated with individuals such as Godfrey Danchimah.
-
E.
Wadaman
Wadaman is an alternative spelling for the Wardaman people, an Aboriginal Australian group traditionally associated with the Victoria River region of the Northern Territory.
- 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_69e2458b4c888190b1d7998f9862a558 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a64c1ee081908ba3adf5ce80d6a5 |
completed | April 29, 2026, 6:33 a.m. |
Created at: April 17, 2026, 5:52 p.m.