Triple
T604601
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Security Agency |
E11566
|
entity |
| Predicate | budgetClassification |
P2120
|
FINISHED |
| Object | classified |
—
|
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: classified | Statement: [National Security Agency, budgetClassification, classified]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: budgetClassification Context triple: [National Security Agency, budgetClassification, classified]
-
A.
budgetType
chosen
Indicates the classification or category of a budget associated with an entity or financial activity.
-
B.
budgetUnit
Indicates that one entity functions as the budgetary unit or cost-accounting unit associated with another entity within a financial or organizational context.
-
C.
budgetLevel
Indicates the relative amount of financial resources allocated or available for something, typically categorized by level (e.g., low, medium, high).
-
D.
budgetSource
Indicates the origin or provider of the funds used to finance a particular activity, project, or expenditure.
-
E.
budgetFunction
Indicates a relationship where a specific budgeting rule or formula determines how resources or funds are allocated or constrained for an entity or activity.
- 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_69a4932779b881908688590d59c71900 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a49e574444819087999404f3e3ffd9 |
completed | March 1, 2026, 8:15 p.m. |
| PD | Predicate disambiguation | batch_69a49cf701e08190966d06b9ff4b582b |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.