Triple
T30422525
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPEs |
E773936
|
entity |
| Predicate | primaryDataAccess |
P59929
|
FINISHED |
| Object | DMA transfers |
—
|
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: DMA transfers | Statement: [SPEs, primaryDataAccess, DMA transfers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryDataAccess Context triple: [SPEs, primaryDataAccess, DMA transfers]
-
A.
primaryDatabase
Indicates that one database serves as the main or authoritative data source in relation to another system or database.
-
B.
primaryDataType
Indicates that one data type is the main or default type associated with a given entity or context, as opposed to any secondary or auxiliary data types.
-
C.
dataAccessModel
chosen
Indicates the framework or scheme that governs how data can be accessed, including who can retrieve it, under what conditions, and through which mechanisms.
-
D.
primaryIndex
Indicates that one entity serves as the main or default index used to organize, access, or reference another entity within a system or dataset.
-
E.
primaryField
Indicates the main area of focus, discipline, or domain most centrally associated with an 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a022348ae2881908eae1be79b6f6ff6 |
completed | May 11, 2026, 6:43 p.m. |
| PD | Predicate disambiguation | batch_6a0220beb6b08190981fb86363757517 |
completed | May 11, 2026, 6:32 p.m. |
Created at: April 29, 2026, 8:06 p.m.