Triple
T9791105
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coronavirus Aid, Relief, and Economic Security Act |
E237608
|
entity |
| Predicate | totalAuthorizedSpending |
P75110
|
FINISHED |
| Object | over $2 trillion |
—
|
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: over $2 trillion | Statement: [Coronavirus Aid, Relief, and Economic Security Act, totalAuthorizedSpending, over $2 trillion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: totalAuthorizedSpending Context triple: [Coronavirus Aid, Relief, and Economic Security Act, totalAuthorizedSpending, over $2 trillion]
-
A.
authorizedSpending
Indicates that an entity has been granted permission to spend or allocate a specified amount of resources, typically funds, under defined conditions.
-
B.
spendSize
Indicates the amount or magnitude of spending associated with an entity or transaction.
-
C.
fundingAuthorizationAmount
chosen
Indicates the specific amount of money that has been formally approved or authorized to fund something.
-
D.
feeTypeAuthorized
Indicates that a particular type of fee is permitted or approved for use in a given context or relationship.
-
E.
supportsSpendingCategory
Indicates that one entity allows, enables, or is compatible with making expenditures in a specified spending category.
- 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_69ca84dc04488190b9c91193976c0960 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda215b3108190a897552e1dc91cc4 |
completed | April 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69cd03d77c6c81909b675955bf113320 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:28 p.m.