Triple
T32178849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paycheck Protection Program |
E821927
|
entity |
| Predicate | endOfNewLoans |
P48547
|
FINISHED |
| Object | 2021-05 |
—
|
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: 2021-05 | Statement: [Paycheck Protection Program, endOfNewLoans, 2021-05]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: endOfNewLoans Context triple: [Paycheck Protection Program, endOfNewLoans, 2021-05]
-
A.
endOf
chosen
Indicates that one entity marks the terminating point or final boundary of another entity, event, or interval.
-
B.
isFinalInstallmentOf
Indicates that one work or item is the concluding or last part in a series, sequence, or collection of related works.
-
C.
alsoEnded
Indicates that one event or state concluded in addition to another already mentioned event or state.
-
D.
canEndOn
Indicates that one entity is allowed or able to terminate, conclude, or finish with another specified entity or condition.
-
E.
loanedFor
Indicates that one entity has been temporarily provided to another entity for a specified purpose, duration, or use under agreed loan conditions.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6c8159edc8190b1c87015e0c820e8 |
completed | May 3, 2026, 3:59 a.m. |
| PD | Predicate disambiguation | batch_69f6c3f42fbc8190a06eb1044c9e6094 |
completed | May 3, 2026, 3:41 a.m. |
Created at: May 1, 2026, 12:34 a.m.