Triple
T19384975
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Big Three credit rating agencies |
E484909
|
entity |
| Predicate | useRatingScales |
P16725
|
FINISHED |
| Object | long-term 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 credit ratings | Statement: [Big Three credit rating agencies, useRatingScales, long-term credit ratings]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: useRatingScales Context triple: [Big Three credit rating agencies, useRatingScales, long-term credit ratings]
-
A.
usesRating
Indicates that one entity applies, relies on, or incorporates a rating assigned to another entity.
-
B.
ratingContext
Indicates the situational or contextual factors under which a rating is given or applies.
-
C.
scoreScale
chosen
Indicates the scale or range on which a score or rating is expressed or measured.
-
D.
ratingDescription
Indicates the textual explanation or qualitative summary associated with a given rating or score.
-
E.
ratingSystem
Indicates a system or method used to assign evaluative scores or rankings to items, actions, or entities based on defined criteria.
- 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.