Triple
T27589843
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | OpenStack Magnum |
E699766
|
entity |
| Predicate | supportsNetworkDriver |
P109386
|
FINISHED |
| Object |
Flannel
Flannel is a simple, open-source virtual network fabric for containers, commonly used with Kubernetes to provide an overlay network for pod communication.
|
E1780767
|
NE FINISHED |
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: Flannel | Statement: [OpenStack Magnum, supportsNetworkDriver, Flannel]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Flannel Triple: [OpenStack Magnum, supportsNetworkDriver, Flannel]
Generated description
Flannel is a simple, open-source virtual network fabric for containers, commonly used with Kubernetes to provide an overlay network for pod communication.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsNetworkDriver Context triple: [OpenStack Magnum, supportsNetworkDriver, Flannel]
-
A.
supportsDriverType
Indicates that one entity is compatible with, or able to operate using, a specified type of driver.
-
B.
supportsNetworkVirtualization
Indicates that one entity provides capabilities or functionality that enable network virtualization for another entity or within a system.
-
C.
supportsContainerRuntime
Indicates that one entity provides compatibility with, or the ability to run and manage, a specified container runtime environment for another entity.
-
D.
supportedNetwork
chosen
Indicates that one entity (such as a device, service, or application) is compatible with, operates on, or is designed to work over a specified network or type of network.
-
E.
deploymentDriver
Indicates a person or system that is responsible for executing, managing, or initiating the deployment of a resource, service, or change.
- F. None of above.
Provenance (6 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_69ef6a4d71f081909a1235763206b691 |
completed | April 27, 2026, 1:53 p.m. |
| NER | Named-entity recognition | batch_69ff3fb2318c81908a46c2f513608935 |
completed | May 9, 2026, 2:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a12d0db67808190aaa54e7499053a60 |
completed | May 24, 2026, 10:20 a.m. |
| NEDg | Description generation | batch_6a12d18c931081909d1620e19d46e1c8 |
completed | May 24, 2026, 10:23 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a12d28db59c8190a9141f9e352f19b4 |
completed | May 24, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69ff3e96dcc48190819f6204680d84aa |
completed | May 9, 2026, 2:03 p.m. |
Created at: April 27, 2026, 2:05 p.m.