Triple
T24142373
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Executive Order 13258 |
E598276
|
entity |
| Predicate | officeAffected |
P1635
|
FINISHED |
| Object | Assistant to the President |
—
|
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: Assistant to the President | Statement: [Executive Order 13258, officeAffected, Assistant to the President]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: officeAffected Context triple: [Executive Order 13258, officeAffected, Assistant to the President]
-
A.
affectsOffice
chosen
Indicates that one entity has an influence or impact on the condition, function, or status of an office.
-
B.
officeInvolved
Indicates that a particular office or organizational unit is involved or participates in a specified event, action, or relationship.
-
C.
officeIs
Indicates that one entity serves as the office or official workplace location of another entity.
-
D.
officeContingentOn
Indicates that holding or obtaining one office, position, or role is dependent on the prior existence, status, or outcome of another specified office or condition.
-
E.
officeAfter
Indicates that one office or term of office occurs chronologically after another office or term.
- 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_69e288c92e448190ac57034fa0c863ce |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1e00832148190b40b904d514a286b |
completed | April 29, 2026, 10:40 a.m. |
| PD | Predicate disambiguation | batch_69f1765650fc8190a6bc1eb512b240bf |
completed | April 29, 2026, 3:09 a.m. |
Created at: April 17, 2026, 11:28 p.m.