Triple
T38638239
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GitHub Container Registry |
E937615
|
entity |
| Predicate | defaultHostname |
P31024
|
FINISHED |
| Object | ghcr.io |
—
|
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: ghcr.io | Statement: [GitHub Container Registry, defaultHostname, ghcr.io]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defaultHostname Context triple: [GitHub Container Registry, defaultHostname, ghcr.io]
-
A.
defaultDomain
chosen
Indicates that one entity serves as the standard or primary domain associated with another entity, used when no more specific domain is specified.
-
B.
naturalHost
Indicates that one entity is the typical or primary host in which another entity (such as a parasite or pathogen) naturally lives, grows, or reproduces.
-
C.
currentHost
Indicates that one entity is the present or active host for another entity or process.
-
D.
hostFullName
Indicates that one entity is the complete personal name (including given and family names, and possibly middle names or titles) of the host associated with another entity.
-
E.
originalHost
Indicates that one entity is the initial or primary host on which another entity first resided, originated, or was hosted.
- 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_69fce545fec881909247a3af821d21ae |
completed | May 7, 2026, 7:17 p.m. |
| PD | Predicate disambiguation | batch_69fce12eaeec81908cf81346b2cef6e0 |
completed | May 7, 2026, 6:59 p.m. |
Created at: May 3, 2026, 4:32 p.m.