Triple
T24993378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maastricht criteria |
E625503
|
entity |
| Predicate | setsLimitType |
P38256
|
FINISHED |
| Object | comparative benchmarks for inflation and interest rates |
—
|
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: comparative benchmarks for inflation and interest rates | Statement: [Maastricht criteria, setsLimitType, comparative benchmarks for inflation and interest rates]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: setsLimitType Context triple: [Maastricht criteria, setsLimitType, comparative benchmarks for inflation and interest rates]
-
A.
typeOfLimit
chosen
Indicates that one entity specifies the category or kind of limit that applies to another entity.
-
B.
definesLimitOf
Indicates that one entity specifies or establishes the maximum or boundary condition applicable to another entity.
-
C.
setsMaximum
Indicates that one entity establishes an upper limit or maximum allowable value for another entity or quantity.
-
D.
hasLimitSet
Indicates that there is a defined boundary, range, or constraint applied to something.
-
E.
gLimit
Indicates a constraint or maximum boundary imposed on the magnitude, rate, or extent of something within a given context.
- 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_69e2ff2611c081908710457fbe6d376b |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f453035f508190be83a3d521723acf |
completed | May 1, 2026, 7:15 a.m. |
| PD | Predicate disambiguation | batch_69f44d77f6e88190a4643ab2cbef567b |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:04 a.m.