Triple
T4894136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | U.S. savings banks |
E109631
|
entity |
| Predicate | productPricing |
P60457
|
FINISHED |
| Object | typically offer interest-bearing savings products |
—
|
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: typically offer interest-bearing savings products | Statement: [U.S. savings banks, productPricing, typically offer interest-bearing savings products]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productPricing Context triple: [U.S. savings banks, productPricing, typically offer interest-bearing savings products]
-
A.
pricingStrategy
Indicates the approach or method used to set, adjust, or structure prices for products or services in a given context.
-
B.
priceDeterminedBy
Indicates that the price of one entity is set, influenced, or calculated based on another entity or factor.
-
C.
priceCategory
Indicates the classification of an item or service based on its price level or cost range.
-
D.
priceReference
Indicates a relationship where one price is used as a benchmark or basis for determining, comparing, or deriving another price.
-
E.
purchasePrice
Indicates the monetary amount paid or agreed to be paid to acquire something in a purchase transaction.
- 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_69bd4410bbf88190aad50d2451c863d6 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ffabccc81909115ece1b04e2061 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2e7b5c8190b8bf9d616dfa24f0 |
completed | March 20, 2026, 3:47 p.m. |
| PDg | Predicate description generation | batch_69bd6ff731188190a9903602122d4ff9 |
completed | March 20, 2026, 4:04 p.m. |
Created at: March 20, 2026, 1:28 p.m.