Triple
T9817773
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surface Laptop Go 3 |
E238451
|
entity |
| Predicate | marketAvailabilityRegion |
P18387
|
FINISHED |
| Object | worldwide |
—
|
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: worldwide | Statement: [Surface Laptop Go 3, marketAvailabilityRegion, worldwide]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marketAvailabilityRegion Context triple: [Surface Laptop Go 3, marketAvailabilityRegion, worldwide]
-
A.
internationalAvailability
chosen
Indicates that something is available or accessible across multiple countries or regions beyond a single national boundary.
-
B.
availableInCountry
Indicates that something can be legally or practically obtained, accessed, or used within a specified country.
-
C.
distributionAvailability
Indicates that a product or resource is available for distribution through a particular channel, location, or method.
-
D.
marketRegion
Indicates the geographic or demographic area in which a product, service, or entity is actively marketed or targeted.
-
E.
supportsRegionRestriction
Indicates that an entity enforces or accommodates limitations on availability or access based on geographic regions.
- 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_69ca84dfde1481909f47c286d715f892 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdb2f5bfa481908a2d2cb3f3d7d585 |
completed | April 2, 2026, 12:06 a.m. |
| PD | Predicate disambiguation | batch_69cd03e01ea881909a7d93fc3994ace5 |
completed | April 1, 2026, 11:39 a.m. |
Created at: March 30, 2026, 8:30 p.m.