Triple
T1292584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Active Cosmetics Division |
E27578
|
entity |
| Predicate | offersProductCategory |
P28338
|
FINISHED |
| Object | facial skincare |
—
|
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: facial skincare | Statement: [Active Cosmetics Division, offersProductCategory, facial skincare]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersProductCategory Context triple: [Active Cosmetics Division, offersProductCategory, facial skincare]
-
A.
offersProduct
Indicates that one entity makes a product available to another entity, typically for sale or use.
-
B.
offersServiceType
Indicates that one entity provides or makes available a specific type or category of service to another entity or the public.
-
C.
offersPlanType
Indicates that one entity provides or makes available a specific type of plan to another entity or in a given context.
-
D.
offersFeature
Indicates that one entity provides or makes available a particular feature or capability to another entity.
-
E.
offersServiceTo
Indicates that one entity provides or makes a service available for the benefit or use of another entity.
- F. None of above. chosen
Provenance (4 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_69a496d4ec448190ad653b2590c46711 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c3bb3a9c81909db2ad91defd87b6 |
completed | March 1, 2026, 10:54 p.m. |
| PD | Predicate disambiguation | batch_69a4bee64d908190b6a9bb479959d523 |
completed | March 1, 2026, 10:34 p.m. |
| PDg | Predicate description generation | batch_69a4c3b9ebdc819098de4d3288201bc1 |
completed | March 1, 2026, 10:54 p.m. |
Created at: March 1, 2026, 7:51 p.m.