Triple
T28627988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wikimedia servers |
E724571
|
entity |
| Predicate | networkRoleIncludes |
P119868
|
FINISHED |
| Object | edge cache |
—
|
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: edge cache | Statement: [Wikimedia servers, networkRoleIncludes, edge cache]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: networkRoleIncludes Context triple: [Wikimedia servers, networkRoleIncludes, edge cache]
-
A.
hasRoleInNetwork
Indicates that an entity holds a specific functional position or responsibility within a particular network.
-
B.
includesRoles
chosen
Indicates that one entity contains or encompasses one or more specified roles within its scope or structure.
-
C.
hasCircuitRole
Indicates that an entity participates in a circuit with a specific functional role or responsibility within that circuit.
-
D.
connectsRole
Indicates a relationship in which one entity is linked to another by assigning or associating a specific role between them.
-
E.
usesRoleTypes
Indicates that an entity employs or is associated with specific role classifications or role types within a given context.
- 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_69f01d822ac08190932de59ec2268ed2 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f67f0488bc819089fbd2d2478158d3 |
completed | May 2, 2026, 10:47 p.m. |
| PD | Predicate disambiguation | batch_69f67e3ed894819094c067c1ef624951 |
completed | May 2, 2026, 10:44 p.m. |
Created at: April 28, 2026, 4:36 a.m.