Triple
T31600942
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brazilian Treasury bonds |
E806345
|
entity |
| Predicate | benchmarkRate |
P23745
|
FINISHED |
| Object | SELIC rate |
—
|
NE NERFINISHED |
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: SELIC rate | Statement: [Brazilian Treasury bonds, benchmarkRate, SELIC rate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: benchmarkRate Context triple: [Brazilian Treasury bonds, benchmarkRate, SELIC rate]
-
A.
benchmarkFamily
Indicates that one entity serves as a benchmark or reference standard for evaluating or comparing another entity within the same family or category.
-
B.
benchmarkFor
chosen
Indicates that one entity serves as a standard or reference point against which the performance, quality, or characteristics of another entity are measured or evaluated.
-
C.
benchmarkProperty
Indicates that a property or attribute is being used as a benchmark or reference standard for evaluating or comparing other entities or values.
-
D.
benchmarkStatus
Indicates the current evaluation state or outcome of a benchmark process applied to an entity or system.
-
E.
benchmarkDomain
Indicates that something serves as a standard or reference point for measuring or evaluating performance within a particular domain or area.
- 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_69f348d54ccc8190a03b5df9a2b40b25 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a86aecd48190b0f9e9fcb4cab449 |
completed | May 3, 2026, 1:44 a.m. |
| PD | Predicate disambiguation | batch_69f6a75656e081908739ed9e2f600e42 |
completed | May 3, 2026, 1:39 a.m. |
Created at: April 30, 2026, 10:32 p.m.