Triple
T3022723
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple Desktop Bus Mouse |
E82499
|
entity |
| Predicate | buttonType |
P44686
|
FINISHED |
| Object | single primary button |
—
|
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: single primary button | Statement: [Apple Desktop Bus Mouse, buttonType, single primary button]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: buttonType Context triple: [Apple Desktop Bus Mouse, buttonType, single primary button]
-
A.
clickType
Indicates the specific kind or category of click interaction that occurred between a user and an interface element.
-
B.
inputType
Indicates the kind or format of data that an entity expects to receive as input in a given context.
-
C.
slotType
Indicates the classification or category assigned to a particular slot or position within a structure, system, or sequence.
-
D.
modeType
Indicates the specific manner, method, or operational mode in which an action, process, or system is carried out or functions.
-
E.
brickButtons
Indicates that one entity presses, activates, or otherwise operates the buttons associated with another entity.
- F. None of above. chosen
Provenance (4 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_69ad8b1fb34081908c1b873e2b7273e1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a963034819093d96566e9b0cea9 |
completed | March 8, 2026, 3:49 p.m. |
| PD | Predicate disambiguation | batch_69ad961c430c8190ac48f2e3c7e7c649 |
completed | March 8, 2026, 3:30 p.m. |
| PDg | Predicate description generation | batch_69ad97f6af3881909f4547967384114c |
completed | March 8, 2026, 3:38 p.m. |
Created at: March 8, 2026, 3 p.m.