Triple
T28595849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Swahili Wikibooks |
E723767
|
entity |
| Predicate | accountProvider |
P74056
|
FINISHED |
| Object | Unified Wikimedia login |
—
|
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: Unified Wikimedia login | Statement: [Swahili Wikibooks, accountProvider, Unified Wikimedia login]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accountProvider Context triple: [Swahili Wikibooks, accountProvider, Unified Wikimedia login]
-
A.
identityProviderType
Indicates the type or category of the identity provider used to authenticate or identify an entity.
-
B.
associatedWithProvider
chosen
Indicates that one entity has a connection or relationship with a specific provider, such as being supplied, managed, or serviced by that provider.
-
C.
credentialFramework
Indicates a formal system or structure within which a credential is defined, organized, or classified.
-
D.
authenticationProperty
Indicates a relationship where an entity is associated with a specific characteristic, method, or parameter used in its authentication process.
-
E.
typicalProvider
Indicates that one entity commonly or characteristically serves as a provider of goods, services, or resources to another entity.
- 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_69f01d80b1908190980594837604b8c7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 28, 2026, 4:21 a.m.