Triple
T13960932
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cash for Clunkers program |
E335788
|
entity |
| Predicate | fundingIncreasedTo |
P64484
|
FINISHED |
| Object | $3 billion |
—
|
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: $3 billion | Statement: [Cash for Clunkers program, fundingIncreasedTo, $3 billion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fundingIncreasedTo Context triple: [Cash for Clunkers program, fundingIncreasedTo, $3 billion]
-
A.
fundingLevel
chosen
Indicates the amount or degree of financial resources allocated or committed to an entity, project, or activity.
-
B.
additionalFunding
Indicates that one entity provides or allocates extra financial resources beyond an initial or existing amount to another entity or project.
-
C.
fundingCommitment
Indicates a promise or obligation by one party to provide a specified amount or type of funding to another party or project.
-
D.
raisedMoneyFor
Indicates that one entity collected or obtained funds specifically to support or benefit another entity, cause, or purpose.
-
E.
possibleAdditionalFunding
Indicates that there is a potential for securing or providing further financial resources beyond what has already been allocated or committed.
- 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_69d81c61f3508190aaf2ca0dc0002c59 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2e7b2f908190aa32f22298964746 |
completed | April 14, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69de05a3ccf88190b45c742db483fa08 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:17 p.m.