Triple
T11906798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Windtraders |
E283290
|
entity |
| Predicate | hasMerchandiseType |
P3585
|
FINISHED |
| Object | customizable souvenirs |
—
|
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: customizable souvenirs | Statement: [Windtraders, hasMerchandiseType, customizable souvenirs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMerchandiseType Context triple: [Windtraders, hasMerchandiseType, customizable souvenirs]
-
A.
hasListedProductType
Indicates that an entity has a product associated with it that is categorized under a specific listed product type.
-
B.
hasProduct
chosen
Indicates that an entity possesses, offers, or is associated with a particular product.
-
C.
hasMerchandiseTieIn
Indicates that one entity has a commercial or promotional product or line (merchandise) that is directly tied to, branded with, or derived from another entity.
-
D.
hasMaterialType
Indicates that something is composed of, made from, or characterized by a specific type of material.
-
E.
hasBrandType
Indicates that an entity is associated with or categorized under a particular brand type or classification.
- 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_69d6ab2c07e88190ba13b0d21fd6cf33 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8e5264b2081909bda6c24abb89725 |
completed | April 10, 2026, 11:55 a.m. |
| PD | Predicate disambiguation | batch_69d8bb3632ac8190b13e53c2b5db7125 |
completed | April 10, 2026, 8:56 a.m. |
Created at: April 8, 2026, 9:44 p.m.