Triple
T4832102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MediaWiki |
E107967
|
entity |
| Predicate | supportsEmailIntegration |
P8841
|
FINISHED |
| Object | email notifications |
—
|
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: email notifications | Statement: [MediaWiki, supportsEmailIntegration, email notifications]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsEmailIntegration Context triple: [MediaWiki, supportsEmailIntegration, email notifications]
-
A.
supportsAccountType
Indicates that one entity is compatible with, or able to operate for, a specified type or category of account.
-
B.
supportsOnlineAccountManagement
Indicates that an entity provides functionality for users to manage their accounts through an online interface or platform.
-
C.
postalIntegration
Indicates a relationship where one system or entity is connected to and can exchange or synchronize data with a postal or mail-handling system.
-
D.
supportsSignInMethod
Indicates that one entity enables or allows another entity to use a particular sign-in or authentication method.
-
E.
typeOfIntegration
chosen
Indicates the specific kind or category of integration that exists or is applied between systems, components, or processes.
- 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_69bd43fac8188190803f0327190621e4 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ff981fc819080d4466c6fe06cf3 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c21c7f08190846049d31fdfa144 |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:24 p.m.