Triple
T12709221
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jodey Arrington |
E303669
|
entity |
| Predicate | supported policy |
P1086
|
FINISHED |
| Object | reduced federal spending |
—
|
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: reduced federal spending | Statement: [Jodey Arrington, supported policy, reduced federal spending]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supported policy Context triple: [Jodey Arrington, supported policy, reduced federal spending]
-
A.
supportsPolicy
chosen
Indicates that one entity endorses, backs, or is in favor of a particular policy or set of policies.
-
B.
supportPolicy
Indicates that one entity endorses, backs, or helps to maintain a particular policy or course of action.
-
C.
supportsPolicyGoal
Indicates that one entity’s actions, positions, or characteristics help advance, uphold, or contribute to achieving a specified policy goal.
-
D.
supportsPolicyArea
Indicates that one entity endorses, advocates for, or is in favor of a particular policy area or domain of public policy.
-
E.
supportedGovernment
Indicates that one entity provided assistance, endorsement, or backing to a particular government or governing authority.
- 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_69d7bdf084148190ab9d513dc0735af4 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96207b2d881908314efc3e350aa78 |
completed | April 10, 2026, 8:48 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
Created at: April 9, 2026, 5:23 p.m.