Triple
T6163210
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Arab Bank for Economic Development in Africa |
E137492
|
entity |
| Predicate | loanTerms |
P9377
|
FINISHED |
| Object | concessional |
—
|
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: concessional | Statement: [Arab Bank for Economic Development in Africa, loanTerms, concessional]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: loanTerms Context triple: [Arab Bank for Economic Development in Africa, loanTerms, concessional]
-
A.
loanStructure
Indicates the specific terms, components, and repayment arrangement that define how a loan is organized between parties.
-
B.
loanType
chosen
Indicates the specific category or kind of loan associated with an entity or transaction.
-
C.
settlementTerm
Indicates the agreed conditions, timing, and method by which an obligation, transaction, or dispute is settled between parties.
-
D.
loanSource
Indicates that one entity is the origin or provider of a loan extended to another entity.
-
E.
creditSchedule
Indicates a planned or agreed-upon timetable for extending, using, or repaying credit between parties.
- 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_69c008a54fc88190b6ce4416490ca79d |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c05d5e8edc8190a7a394ee832bac9f |
completed | March 22, 2026, 9:21 p.m. |
| PD | Predicate disambiguation | batch_69c055f5b81481908819515cdc334ae6 |
completed | March 22, 2026, 8:49 p.m. |
Created at: March 22, 2026, 4:17 p.m.