Triple
T7790172
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kasoa |
E187355
|
entity |
| Predicate | nearbyTown |
P3883
|
FINISHED |
| Object |
Weija
Weija is a suburban community in the Greater Accra Region of Ghana, known for the Weija Dam and its role in supplying water to Accra and surrounding areas.
|
E693635
|
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: Weija | Statement: [Kasoa, nearbyTown, Weija]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Weija Context triple: [Kasoa, nearbyTown, Weija]
-
A.
Niani
Niani was an important medieval West African city that served as the political and commercial center of the Mali Empire.
-
B.
Yakurr
Yakurr is a local government area in southeastern Nigeria known for its rich cultural heritage and predominantly agrarian communities.
-
C.
Abdju
Abdju is the ancient Egyptian name for Abydos, one of Egypt’s oldest and most sacred cities, renowned as a major cult center of Osiris and a royal burial site.
-
D.
Djenne
Djenné is an ancient trading city in present-day Mali renowned for its mud-brick architecture and historic role as a center of Islamic scholarship and trans-Saharan commerce.
-
E.
Ikwerre
Ikwerre is a Niger-Congo language spoken primarily by the Ikwerre people in Rivers State, Nigeria, particularly in and around Port Harcourt.
- 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: Weija Triple: [Kasoa, nearbyTown, Weija]
Generated description
Weija is a suburban community in the Greater Accra Region of Ghana, known for the Weija Dam and its role in supplying water to Accra and surrounding areas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Weija Target entity description: Weija is a suburban community in the Greater Accra Region of Ghana, known for the Weija Dam and its role in supplying water to Accra and surrounding areas.
-
A.
Niani
Niani was an important medieval West African city that served as the political and commercial center of the Mali Empire.
-
B.
Yakurr
Yakurr is a local government area in southeastern Nigeria known for its rich cultural heritage and predominantly agrarian communities.
-
C.
Abdju
Abdju is the ancient Egyptian name for Abydos, one of Egypt’s oldest and most sacred cities, renowned as a major cult center of Osiris and a royal burial site.
-
D.
Djenne
Djenné is an ancient trading city in present-day Mali renowned for its mud-brick architecture and historic role as a center of Islamic scholarship and trans-Saharan commerce.
-
E.
Ikwerre
Ikwerre is a Niger-Congo language spoken primarily by the Ikwerre people in Rivers State, Nigeria, particularly in and around Port Harcourt.
- 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_69ca82af2d2c8190963861f5e0b8bf21 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cae7ea13f08190a60c5f1863bce816 |
completed | March 30, 2026, 9:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69caf62c8568819090c058b0c55b7865 |
completed | March 30, 2026, 10:16 p.m. |
| NEDg | Description generation | batch_69caf820b05481908b405048c077ca2e |
completed | March 30, 2026, 10:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cafa052d4481908b89f6001aa6ea01 |
completed | March 30, 2026, 10:32 p.m. |
Created at: March 30, 2026, 4:25 p.m.