Triple
T28610963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | qemu-nbd |
E724165
|
entity |
| Predicate | upstreamRepository |
P11905
|
FINISHED |
| Object | QEMU source code repository |
—
|
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: QEMU source code repository | Statement: [qemu-nbd, upstreamRepository, QEMU source code repository]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upstreamRepository Context triple: [qemu-nbd, upstreamRepository, QEMU source code repository]
-
A.
upstreamFrom
Indicates that one entity is located or occurs earlier in the flow or sequence relative to another, typically in a direction opposite to the main movement or progression.
-
B.
previousRepository
Indicates that one repository directly precedes another in a version, history, or sequence of repositories.
-
C.
usesUpstreamProject
chosen
Indicates that one entity depends on, incorporates, or builds upon another entity as an upstream project in its development or operation.
-
D.
upstreamNameVariant
Indicates that one name is an alternative or variant form of another name that is considered the primary or source (upstream) version.
-
E.
repositoryUrl
Indicates the web address where the related code, data, or resources are stored and managed in a version-controlled repository.
- 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_69f01d816d7c8190a1fe27e3434041dc |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f652a492108190b885b955ce147d3c |
completed | May 2, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69f651aad92c8190b874b3b5f9f64434 |
completed | May 2, 2026, 7:34 p.m. |
Created at: April 28, 2026, 4:30 a.m.