Triple
T38635888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Microsoft Graph Java SDK |
E937571
|
entity |
| Predicate | accessesAPI |
P31856
|
FINISHED |
| Object | Microsoft Graph API |
—
|
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: Microsoft Graph API | Statement: [Microsoft Graph Java SDK, accessesAPI, Microsoft Graph API]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessesAPI Context triple: [Microsoft Graph Java SDK, accessesAPI, Microsoft Graph API]
-
A.
hasAPIs
chosen
Indicates that one entity provides or exposes application programming interfaces (APIs) that can be used or accessed by another entity.
-
B.
APIType
Indicates the type or category of an API associated with or used by an entity.
-
C.
accessedFor
Indicates that one entity is used to obtain entry to, retrieve, or make use of another entity.
-
D.
apiFunction
Indicates that one entity is a callable operation or method provided by an API that another entity can invoke to perform a specific task or retrieve data.
-
E.
relatedAPI
Indicates that one API has a defined relationship or association with another API, such as dependency, integration, or functional linkage.
- 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_69f76ed5ca3c81909288f61fbf37b359 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fcdfbc71c481908ba7f87907b17782 |
completed | May 7, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe580b8819087f143596b2c79c0 |
completed | May 7, 2026, 6:37 p.m. |
Created at: May 3, 2026, 4:32 p.m.