Triple
T1474522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | African Development Bank |
E30807
|
entity |
| Predicate | hasRegionalMemberCountries |
P17966
|
FINISHED |
| Object | African Union member states |
—
|
LITERAL 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: African Union member states | Statement: [African Development Bank, hasRegionalMemberCountries, African Union member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRegionalMemberCountries Context triple: [African Development Bank, hasRegionalMemberCountries, African Union member states]
-
A.
memberStatesAreMemberOf
chosen
Indicates that certain states belong to or hold membership in a particular organization, group, or union.
-
B.
participantsRegion
Indicates that the related entities are associated with, originate from, or operate within a specified geographic region.
-
C.
countryJoined
Indicates that a country became a member of, or formally entered into, a specific organization, union, alliance, or agreement.
-
D.
countryOfOriginOfMembers
Indicates that one entity is the country from which the members of another entity originate.
-
E.
hasNumberOfCountries
Indicates the relationship that specifies how many countries are associated with or contained within a given entity.
- F. None of above.
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_69a498fe55a88190ab7f9e40ace88e49 |
completed | March 1, 2026, 7:52 p.m. |
| NER | Named-entity recognition | batch_69a4c6011d248190988380eca4ecf514 |
completed | March 1, 2026, 11:04 p.m. |
| PD | Predicate disambiguation | batch_69a4c48350d88190a81bd149103f93e3 |
completed | March 1, 2026, 10:58 p.m. |
Created at: March 1, 2026, 8:11 p.m.