Triple
T3018639
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kurmi Market |
E82398
|
entity |
| Predicate | goodsType |
P28339
|
FINISHED |
| Object | handicrafts |
—
|
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: handicrafts | Statement: [Kurmi Market, goodsType, handicrafts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: goodsType Context triple: [Kurmi Market, goodsType, handicrafts]
-
A.
garmentType
Indicates the specific kind or category of garment associated with an entity.
-
B.
categoryIUsedFor
Indicates that one entity is used as a category or classification label for another entity.
-
C.
productDomain
Indicates the domain, field, or area of application to which a given product belongs or is relevant.
-
D.
notableProductType
chosen
Indicates that an entity is particularly well-known or distinguished for producing or offering a specific type of product.
-
E.
productForm
Indicates the specific physical or presentation format in which a product is offered or delivered (e.g., tablet, liquid, package type).
- 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_69ad8b1fb34081908c1b873e2b7273e1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a927b608190ba1392498507b237 |
completed | March 8, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69ad961a97188190809dc73430a8eda8 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.