Triple
T16493501
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latin American debt crisis |
E400622
|
entity |
| Predicate | hasMainDebtType |
P116335
|
FINISHED |
| Object | sovereign external debt |
—
|
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 external debt | Statement: [Latin American debt crisis, hasMainDebtType, sovereign external debt]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMainDebtType Context triple: [Latin American debt crisis, hasMainDebtType, sovereign external debt]
-
A.
typeOfDebtManaged
chosen
Indicates the specific category or kind of debt that is being handled or overseen in the described relationship or context.
-
B.
hasTypeOfCredit
Indicates that an entity is associated with or characterized by a specific type or category of credit.
-
C.
hasMainInstallment
Indicates that one entity is the primary or principal installment (e.g., main payment or main part of a series) associated with another entity.
-
D.
hasDepositType
Indicates that an entity is associated with or classified by a particular type of deposit.
-
E.
collateralType
Indicates the kind or category of collateral associated with an obligation, agreement, or financial exposure.
- 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_69d883813098819084f5409539723b59 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32e3189c8819097e6ba62f24b1f6c |
completed | April 18, 2026, 7:09 a.m. |
| PD | Predicate disambiguation | batch_69e296902d6c8190884ddb612b8c5b36 |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:13 a.m.