Triple
T38637934
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DreamSpark |
E937609
|
entity |
| Predicate | softwareVendor |
P149792
|
FINISHED |
| Object | Microsoft |
—
|
NE NERFINISHED |
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: Microsoft | Statement: [DreamSpark, softwareVendor, Microsoft]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: softwareVendor Context triple: [DreamSpark, softwareVendor, Microsoft]
-
A.
technologyVendor
chosen
Indicates that one entity serves as the provider or supplier of technology products or services to another entity.
-
B.
architectureVendor
Indicates that one entity serves as the provider or supplier of architectural services, solutions, or products to another entity.
-
C.
vendorType
Indicates the classification or category of a vendor based on the type of goods or services they provide.
-
D.
osVendor
Indicates that one entity is the vendor or provider of an operating system associated with another entity.
-
E.
securityVendor
Indicates that one entity acts as a provider or supplier of security-related products or services to another entity.
- 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdfbc71c481908ba7f87907b17782 |
completed | May 7, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe580b8819087f143596b2c79c0 |
completed | May 7, 2026, 6:37 p.m. |
Created at: May 3, 2026, 4:32 p.m.