Triple
T7577758
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Disney Bundle |
E179400
|
entity |
| Predicate | discounts |
P9238
|
FINISHED |
| Object | combined price compared to separate subscriptions |
—
|
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: combined price compared to separate subscriptions | Statement: [Disney Bundle, discounts, combined price compared to separate subscriptions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discounts Context triple: [Disney Bundle, discounts, combined price compared to separate subscriptions]
-
A.
discountRate
Indicates the percentage or amount by which a price, cost, or value is reduced relative to its original level.
-
B.
offersDiscountsOn
chosen
Indicates that one entity provides price reductions or special discount deals specifically applied to another entity or its associated items or services.
-
C.
fareDiscount
Indicates that a reduced price is applied to a standard fare for a product or service.
-
D.
promotionConditions
Indicates the conditions or criteria that must be met for a promotion to occur between entities.
-
E.
couponFloor
Indicates the minimum coupon rate or value applicable in a financial or discount arrangement, below which the coupon cannot fall.
- 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_69c69f327db881909a21ae3b156f8ded |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f94cdbec81909f2ba7ce04e49931 |
completed | March 27, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69c6f4e04c2c8190a889d928515d9b8e |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:51 p.m.