Triple
T11913544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Takoradi |
E283453
|
entity |
| Predicate | isTwinCityWith |
P1072
|
FINISHED |
| Object | Sekondi |
E279688
|
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: Sekondi | Statement: [Takoradi, isTwinCityWith, Sekondi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sekondi Context triple: [Takoradi, isTwinCityWith, Sekondi]
-
A.
Sekondi
chosen
Sekondi is a coastal city in southwestern Ghana that developed into an important commercial and transportation hub during the colonial era.
-
B.
Sekyiwa
Sekyiwa is the younger half-sister of the late rapper Tupac Shakur and an advocate involved in community and social justice work.
-
C.
Dambai
Dambai is a town in eastern Ghana that serves as the administrative and commercial hub of the Oti Region.
-
D.
Kaneshie
Kaneshie is a bustling suburb of Accra, Ghana, known for its major transport hub and vibrant commercial activity.
-
E.
Ikorodu
Ikorodu is a rapidly growing suburban city and local government area in the northeastern part of Lagos State, Nigeria, known for its residential communities and emerging commercial activity.
- 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_69d6ab2c07e88190ba13b0d21fd6cf33 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e52a2bc08190b80cc6ccf5779d7c |
completed | April 10, 2026, 11:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f4186938548190b5ae10e111aece9a |
completed | May 1, 2026, 3:05 a.m. |
Created at: April 8, 2026, 9:44 p.m.