Triple
T25789876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | EU budget |
E649519
|
entity |
| Predicate | hasSpendingCeiling |
P125398
|
FINISHED |
| Object | around 1 percent of EU gross national income |
—
|
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: around 1 percent of EU gross national income | Statement: [EU budget, hasSpendingCeiling, around 1 percent of EU gross national income]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSpendingCeiling Context triple: [EU budget, hasSpendingCeiling, around 1 percent of EU gross national income]
-
A.
authorizedSpending
Indicates that an entity has been granted permission to spend or allocate a specified amount of resources, typically funds, under defined conditions.
-
B.
hasMaximumBalanceLimit
Indicates that there is an upper bound on the balance that an account or entity is allowed to hold.
-
C.
hasOutOfPocketLimit
Indicates that there is a maximum amount an individual must pay out of pocket for covered services before additional costs are fully or largely covered.
-
D.
monetaryLimit
chosen
Indicates a constraint or maximum allowable amount of money associated with an action, transaction, or relationship.
-
E.
deficitLimit
Indicates a constraint or maximum allowable amount on how large a deficit (shortfall or negative balance) may be.
- 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_69e7ab33e9308190afe415dc6f9e8876 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f69383222c81909d8baa04129d5c81 |
completed | May 3, 2026, 12:14 a.m. |
| PD | Predicate disambiguation | batch_69f690eb1e948190aab41a89969519a5 |
completed | May 3, 2026, 12:03 a.m. |
Created at: April 22, 2026, 5:58 a.m.