Triple
T4399214
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Simpson–Bowles deficit reduction plan |
E99570
|
entity |
| Predicate | proposedEntitlementChange |
P21476
|
FINISHED |
| Object | Social Security reform |
—
|
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: Social Security reform | Statement: [Simpson–Bowles deficit reduction plan, proposedEntitlementChange, Social Security reform]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proposedEntitlementChange Context triple: [Simpson–Bowles deficit reduction plan, proposedEntitlementChange, Social Security reform]
-
A.
claimsToModify
Indicates that one entity asserts it can change, alter, or adjust another entity or its properties.
-
B.
proposedAmendment
chosen
Indicates that one entity has formally suggested a change or addition (an amendment) to another entity, such as a document, law, or agreement.
-
C.
changeReason
Indicates the reason or justification for a modification or change made to an entity or its state.
-
D.
mayAmend
Indicates that one party has the authority or permission to modify, revise, or change something that already exists.
-
E.
changePolicy
Indicates that an entity modifies, replaces, or updates an existing policy governing rules, procedures, or behaviors.
- 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_69b345506b408190b0e3dee616738a7d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b352cc4ab081908bc45d2f76cd4da8 |
completed | March 12, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69b34f597998819092477efdedb51427 |
completed | March 12, 2026, 11:42 p.m. |
Created at: March 12, 2026, 11:20 p.m.