Triple
T7461244
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | FRNs |
E176252
|
entity |
| Predicate | couponFloor |
P77234
|
FINISHED |
| Object | may be zero if reference rate plus spread is non-positive |
—
|
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: may be zero if reference rate plus spread is non-positive | Statement: [FRNs, couponFloor, may be zero if reference rate plus spread is non-positive]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: couponFloor Context triple: [FRNs, couponFloor, may be zero if reference rate plus spread is non-positive]
-
A.
discountRate
Indicates the percentage or amount by which a price, cost, or value is reduced relative to its original level.
-
B.
salePriceApproximate
Indicates that the recorded sale price is an estimated or approximate value rather than an exact amount.
-
C.
priceInfluencedBy
Indicates that the price of one entity is affected or determined by another specified factor or entity.
-
D.
fareDiscount
Indicates that a reduced price is applied to a standard fare for a product or service.
-
E.
priceRelationship
Indicates a comparative relationship between the prices of two entities, such as one being higher, lower, or equal to the other.
- F. None of above. chosen
Provenance (4 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_69c69f21632481908bf83f6c6da897e3 |
completed | March 27, 2026, 3:15 p.m. |
| NER | Named-entity recognition | batch_69c6f3d6cf8c8190a31cac121d151d78 |
completed | March 27, 2026, 9:17 p.m. |
| PD | Predicate disambiguation | batch_69c6f03bad9c8190bdd5abb86d37df47 |
completed | March 27, 2026, 9:01 p.m. |
| PDg | Predicate description generation | batch_69c6f386daac81908ded91b397b44148 |
completed | March 27, 2026, 9:15 p.m. |
Created at: March 27, 2026, 3:38 p.m.