Triple
T34790284
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Export Credit Guarantee Program (GSM-102) |
E1002925
|
entity |
| Predicate | typicalTenor |
P84192
|
FINISHED |
| Object | up to 18 months |
—
|
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: up to 18 months | Statement: [Export Credit Guarantee Program (GSM-102), typicalTenor, up to 18 months]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalTenor Context triple: [Export Credit Guarantee Program (GSM-102), typicalTenor, up to 18 months]
-
A.
typicalTerm
Indicates that something is a standard, representative, or characteristic term typically associated with a given concept or context.
-
B.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
C.
typicalLength
Indicates the usual or characteristic length associated with an entity or phenomenon.
-
D.
typicalHighestLevel
Indicates the usual or most common maximum level or degree that something typically reaches within a given context.
-
E.
typicalPeriod
chosen
Indicates the usual or characteristic time interval or duration associated with an event, process, or state.
- 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_69f76db47d408190a24fc7164439ea2d |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_6a037c8c34f88190ace26f555827f23e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379fd7aac8190873077e63873aa72 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 3:59 p.m.