Triple
T19385070
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BBB |
E484911
|
entity |
| Predicate | scaleContext |
P93346
|
FINISHED |
| Object | long-term issuer credit ratings |
—
|
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: long-term issuer credit ratings | Statement: [BBB, scaleContext, long-term issuer credit ratings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scaleContext Context triple: [BBB, scaleContext, long-term issuer credit ratings]
-
A.
scaleProperty
Indicates that one entity defines or modifies the scale, magnitude, or proportional sizing used to interpret or represent a property of another entity.
-
B.
scaleFunction
Indicates a relationship where one entity defines how another entity’s values are proportionally adjusted or transformed according to a scaling rule or factor.
-
C.
scaleDefinition
chosen
Indicates that an entity specifies the parameters, structure, or measurement system used to define a particular scale.
-
D.
scaleOptimizedFor
Indicates that something has been adjusted or configured to operate most efficiently at a particular size, level, or magnitude.
-
E.
scalingProperty
Indicates how a quantity or behavior changes in proportion to changes in another variable, typically under resizing or rescaling conditions.
- 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_69d8e8d460d88190abf0591c5c9d2b0c |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e61b3ffa548190a060d6e94562a5d2 |
completed | April 20, 2026, 12:25 p.m. |
| PD | Predicate disambiguation | batch_69e4fd602f008190aa9bc76ae17e4ce1 |
completed | April 19, 2026, 4:05 p.m. |
Created at: April 10, 2026, 1:35 p.m.