Triple
T2972094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | subregional offices network of the United Nations Economic Commission for Africa |
E80303
|
entity |
| Predicate | hasSubregionalOffice |
P747
|
FINISHED |
| Object | ECA Subregional Office for Eastern Africa |
E15245
|
NE FINISHED |
How this triple was built (3 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: ECA Subregional Office for Eastern Africa | Statement: [subregional offices network of the United Nations Economic Commission for Africa, hasSubregionalOffice, ECA Subregional Office for Eastern Africa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ECA Subregional Office for Eastern Africa Context triple: [subregional offices network of the United Nations Economic Commission for Africa, hasSubregionalOffice, ECA Subregional Office for Eastern Africa]
-
A.
ECA Subregional Office for Eastern Africa
chosen
The ECA Subregional Office for Eastern Africa is a regional arm of the UN Economic Commission for Africa that supports economic and social development, regional integration, and policy coordination among Eastern African countries.
-
B.
ECA Subregional Office for Central Africa
The ECA Subregional Office for Central Africa is a regional arm of the UN Economic Commission for Africa that supports economic and social development, regional integration, and policy coordination among Central African countries.
-
C.
ECA Subregional Office for Southern Africa
The ECA Subregional Office for Southern Africa is a regional arm of the UN Economic Commission for Africa that supports economic and social development, regional integration, and policy coordination among Southern African countries.
-
D.
ECA Subregional Office for West Africa
The ECA Subregional Office for West Africa is a regional arm of the UN Economic Commission for Africa that supports economic and social development, regional integration, and policy coordination among West African countries.
-
E.
ECA Subregional Office for North Africa
The ECA Subregional Office for North Africa is a regional branch of the UN Economic Commission for Africa that supports economic and social development initiatives in North African countries through research, policy advice, and technical assistance.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubregionalOffice Context triple: [subregional offices network of the United Nations Economic Commission for Africa, hasSubregionalOffice, ECA Subregional Office for Eastern Africa]
-
A.
hasInternationalOrganizationOffice
Indicates that an international organization maintains an official office or physical presence at a given location.
-
B.
hasSubnationalCounterpart
Indicates that an entity has a corresponding or equivalent entity at a lower (subnational) administrative level.
-
C.
hasSubdivision
chosen
Indicates that one entity is divided into and contains another entity as one of its constituent parts or administrative units.
-
D.
hasSupportingOffice
Indicates that an entity is associated with or served by a particular office that provides support or administrative services to it.
-
E.
hasSubregionStatus
Indicates that one region holds an official or defined status as a subregion within a larger geographic or administrative area.
- F. None of above.
Provenance (4 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_69ad8b14ffe881908ffed62f9595c867 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad998656948190ba79d7196d735f34 |
completed | March 8, 2026, 3:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b0fca910e481909c1d93b512a779aa |
completed | March 11, 2026, 5:24 a.m. |
| PD | Predicate disambiguation | batch_69ad960e71f8819088179d11248c6ed0 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:58 p.m.