Triple
T22803019
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rosie the waitress |
E564450
|
entity |
| Predicate | productCategoryAdvertised |
P36108
|
FINISHED |
| Object | paper towels |
—
|
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: paper towels | Statement: [Rosie the waitress, productCategoryAdvertised, paper towels]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productCategoryAdvertised Context triple: [Rosie the waitress, productCategoryAdvertised, paper towels]
-
A.
offersProductCategory
Indicates that a provider or seller makes products belonging to a specific product category available.
-
B.
productTypePromoted
chosen
Indicates that a particular type or category of product is being actively promoted or highlighted, such as through marketing, placement, or special offers.
-
C.
productDomain
Indicates the domain, field, or area of application to which a given product belongs or is relevant.
-
D.
marketedProducts
Indicates that an entity promotes, sells, or otherwise brings specific products to market.
-
E.
productFor
Indicates that one entity is intended to be used by, with, or in relation to another entity as its product or offering.
- 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_69e245823f4c8190ade442cdcc2c224a |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cdf1e308190a05d0f61856be544 |
completed | April 29, 2026, 3:37 a.m. |
| PD | Predicate disambiguation | batch_69eed2cb30f481909566369f515f6eff |
completed | April 27, 2026, 3:06 a.m. |
Created at: April 17, 2026, 3:31 p.m.