Triple
T18015853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NumPy Developers |
E430996
|
entity |
| Predicate | repositoryHostedAt |
P16030
|
FINISHED |
| Object | GitHub |
—
|
NE NERFINISHED |
How this triple was built (3 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: GitHub | Statement: [NumPy Developers, repositoryHostedAt, GitHub]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: GitHub Context triple: [NumPy Developers, repositoryHostedAt, GitHub]
-
A.
GitHub
chosen
GitHub is a widely used web-based platform for version control and collaborative software development, built around the Git system and popular among open-source and enterprise projects.
-
B.
GitLab
GitLab is a web-based DevOps platform that provides Git repository hosting along with integrated tools for source code management, CI/CD, and project collaboration.
-
C.
Bitbucket
Bitbucket is a web-based platform for hosting Git repositories that provides source code management, collaboration tools, and integration with development workflows.
-
D.
Git
Git is a widely used distributed version control system designed to efficiently track changes in source code and support collaborative software development.
-
E.
GitHub API v4
GitHub API v4 is GitHub’s GraphQL-based API that enables flexible, efficient querying and manipulation of GitHub data and resources.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: repositoryHostedAt Context triple: [NumPy Developers, repositoryHostedAt, GitHub]
-
A.
originallyHostedAt
Indicates the location or venue where something was first hosted or took place before any subsequent moves or changes.
-
B.
hostedOn
chosen
Indicates that one entity operates, resides, or is made available on another entity that provides the underlying platform or infrastructure.
-
C.
repositoryUrl
Indicates the web address where the related code, data, or resources are stored and managed in a version-controlled repository.
-
D.
hostedFrom
Indicates that something (such as a service, application, or event) is provided, run, or made available starting from a particular location, source, or environment.
-
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_69d8b904530081908bf341d842464856 |
completed | April 10, 2026, 8:47 a.m. |
| NER | Named-entity recognition | batch_69e4b523f588819097389e067dda7f23 |
completed | April 19, 2026, 10:57 a.m. |
| PD | Predicate disambiguation | batch_69e3f904b8048190add43883cd7cb191 |
completed | April 18, 2026, 9:35 p.m. |
Created at: April 10, 2026, 10:24 a.m.