Triple
T134847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | National Intelligence Program |
E2725
|
entity |
| Predicate | discloses |
P5035
|
FINISHED |
| Object | top-line budget figure annually |
—
|
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: top-line budget figure annually | Statement: [National Intelligence Program, discloses, top-line budget figure annually]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discloses Context triple: [National Intelligence Program, discloses, top-line budget figure annually]
-
A.
describes
Indicates that one entity provides an explanation, representation, or account of another entity or concept.
-
B.
declassified
Indicates that information or material has been officially downgraded from a restricted or secret status, making it accessible to a wider audience or the public.
-
C.
discourages
Indicates an action or influence that deters, dissuades, or reduces the likelihood of someone performing a particular behavior or pursuing a certain outcome.
-
D.
confessedTo
Indicates that one entity admitted guilt or revealed the truth about an action, wrongdoing, or secret to another entity.
-
E.
expresses
Indicates that one entity conveys, communicates, or articulates a thought, feeling, or idea through another medium or form.
- F. None of above. chosen
Provenance (4 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_69a2520c0f3481908b0ed054a2fca8d0 |
completed | Feb. 28, 2026, 2:25 a.m. |
| NER | Named-entity recognition | batch_69a257a3ad908190b6a8652f09ae0cbb |
completed | Feb. 28, 2026, 2:49 a.m. |
| PD | Predicate disambiguation | batch_69a25650251c81908a6ea6368cd61198 |
completed | Feb. 28, 2026, 2:43 a.m. |
| PDg | Predicate description generation | batch_69a256ea776081908fec36c3fdfb8d84 |
completed | Feb. 28, 2026, 2:46 a.m. |
Created at: Feb. 28, 2026, 2:30 a.m.