Triple
T38636917
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Winget |
E937590
|
entity |
| Predicate | primaryRepositoryURL |
P33323
|
FINISHED |
| Object | https://github.com/microsoft/winget-pkgs |
—
|
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: https://github.com/microsoft/winget-pkgs | Statement: [Winget, primaryRepositoryURL, https://github.com/microsoft/winget-pkgs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryRepositoryURL Context triple: [Winget, primaryRepositoryURL, https://github.com/microsoft/winget-pkgs]
-
A.
repositoryUrl
Indicates the web address where the related code, data, or resources are stored and managed in a version-controlled repository.
-
B.
registryURL
Indicates the web address where an entity’s official registration information is stored or can be accessed.
-
C.
previousRepository
Indicates that one repository directly precedes another in a version, history, or sequence of repositories.
-
D.
officialRepositoryFor
chosen
Indicates that one entity serves as the primary, authoritative repository or source for another entity.
-
E.
repositoryName
Indicates the name assigned to a specific repository within a version control or storage system.
- 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_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.