Triple
T22720280
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bono East Region |
E561839
|
entity |
| Predicate | hasMajorTown |
P316
|
FINISHED |
| Object | Yeji |
—
|
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: Yeji | Statement: [Bono East Region, hasMajorTown, Yeji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yeji Context triple: [Bono East Region, hasMajorTown, Yeji]
-
A.
Yeji
chosen
Yeji is a town in central Ghana situated on the shores of Lake Volta, known as a local fishing and trading hub.
-
B.
Yeon
Yeon is the given name of King Seonjo, a Joseon dynasty monarch who ruled Korea during the late 16th century, including the period of the Japanese invasions.
-
C.
Yeomna
Yeomna is the Korean deity of the underworld, serving as the judge of the dead who determines the fate of souls in the afterlife.
-
D.
Yei
Yei is a town in southwestern South Sudan that serves as a regional hub near the borders with Uganda and the Democratic Republic of the Congo.
-
E.
Jejueo
Jejueo is a Koreanic language variety traditionally spoken on South Korea’s Jeju Island, recognized by many linguists as distinct from standard Korean.
- 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_69e2454fc984819088213b58ee87a002 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f17910deb48190b38174e16868f3dd |
completed | April 29, 2026, 3:20 a.m. |
Created at: April 17, 2026, 3:19 p.m.