Triple
T6364464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Upper East Region |
E143190
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Bawku
Bawku is a town in northeastern Ghana known as a commercial hub near the country’s border with Burkina Faso.
|
E588472
|
NE FINISHED |
How this triple was built (4 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: Bawku | Statement: [Upper East Region, hasSettlement, Bawku]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bawku Context triple: [Upper East Region, hasSettlement, Bawku]
-
A.
Bagana
Bagana is an active stratovolcano on Bougainville Island in Papua New Guinea, known for its frequent eruptions and extensive lava flows.
-
B.
Bhamo
Bhamo is a town in northern Myanmar situated on the Ayeyarwady River, historically important as a trading hub near the Chinese border.
-
C.
Nandom
Nandom is a town and district capital in Ghana’s Upper West Region, known for its predominantly Dagara population and proximity to the Burkina Faso border.
-
D.
Sagbama
Sagbama is a town and local government area in Bayelsa State in Nigeria’s Niger Delta region, known for its riverine communities and oil-rich environment.
-
E.
Gashua
Gashua is a town in northeastern Nigeria that serves as an important commercial and administrative center in Yobe State.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Bawku Triple: [Upper East Region, hasSettlement, Bawku]
Generated description
Bawku is a town in northeastern Ghana known as a commercial hub near the country’s border with Burkina Faso.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bawku Target entity description: Bawku is a town in northeastern Ghana known as a commercial hub near the country’s border with Burkina Faso.
-
A.
Bagana
Bagana is an active stratovolcano on Bougainville Island in Papua New Guinea, known for its frequent eruptions and extensive lava flows.
-
B.
Bhamo
Bhamo is a town in northern Myanmar situated on the Ayeyarwady River, historically important as a trading hub near the Chinese border.
-
C.
Nandom
Nandom is a town and district capital in Ghana’s Upper West Region, known for its predominantly Dagara population and proximity to the Burkina Faso border.
-
D.
Sagbama
Sagbama is a town and local government area in Bayelsa State in Nigeria’s Niger Delta region, known for its riverine communities and oil-rich environment.
-
E.
Gashua
Gashua is a town in northeastern Nigeria that serves as an important commercial and administrative center in Yobe State.
- F. None of above. chosen
Provenance (5 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_69c008d8c61081908bcaf61510d881ed |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0680ed0148190b6e310b15b3449ff |
completed | March 22, 2026, 10:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c62d7a1cbc8190a27a0a8e8b466ad5 |
completed | March 27, 2026, 7:10 a.m. |
| NEDg | Description generation | batch_69c62ebcd35481909acd54a5b41f99aa |
completed | March 27, 2026, 7:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c62f5024148190915c9495a9e204b1 |
completed | March 27, 2026, 7:18 a.m. |
Created at: March 22, 2026, 4:32 p.m.