Triple
T2050188
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Development Bank |
E45545
|
entity |
| Predicate | lendingInstruments |
P9377
|
FINISHED |
| Object | sovereign loans |
—
|
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: sovereign loans | Statement: [New Development Bank, lendingInstruments, sovereign loans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lendingInstruments Context triple: [New Development Bank, lendingInstruments, sovereign loans]
-
A.
lendingArm
Indicates that one entity provides financial support or resources to another, typically in the form of a loan or credit.
-
B.
lenderType
Indicates the classification or category of the lender involved in a lending relationship (e.g., bank, individual, institution).
-
C.
tradeInstrument
Indicates a relationship where one entity is used as a financial or commercial instrument in a trade or transaction involving another entity.
-
D.
loanType
chosen
Indicates the specific category or kind of loan associated with an entity or transaction.
-
E.
lender
Indicates a relationship where one party provides something, typically money or resources, to another with the expectation of repayment or return.
- 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_69a8891948208190ab7898da21824c77 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb98e10d48190bb96cd1f8ea3c08b |
completed | March 7, 2026, 5:37 a.m. |
| PD | Predicate disambiguation | batch_69abb7abba508190b872f345d3ba51bb |
completed | March 7, 2026, 5:29 a.m. |
Created at: March 4, 2026, 7:39 p.m.