Triple
T5609548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Niigata Sake no Jin |
E147317
|
entity |
| Predicate | productTypeFeatured |
P36108
|
FINISHED |
| Object | nihonshu |
—
|
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: nihonshu | Statement: [Niigata Sake no Jin, productTypeFeatured, nihonshu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: productTypeFeatured Context triple: [Niigata Sake no Jin, productTypeFeatured, nihonshu]
-
A.
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.
-
B.
featuresShop
Indicates that an entity prominently presents or includes a particular shop as one of its notable elements or offerings.
-
C.
featuresProductAnnouncement
Indicates that something includes or presents a product announcement as part of its content or offering.
-
D.
productForm
Indicates the specific physical or presentation format in which a product is offered or delivered (e.g., tablet, liquid, package type).
-
E.
productFamily
Indicates that one product belongs to, or is categorized under, a broader product family or line.
- 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_69c0090500f881908374285baf0ac46f |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c020fe7ee0819088ced51afd9a4f93 |
completed | March 22, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69c01b1b3c98819080687d18ab10a914 |
completed | March 22, 2026, 4:38 p.m. |
Created at: March 22, 2026, 3:39 p.m.