Triple
T72865
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Apple Macintosh computers |
E1458
|
entity |
| Predicate | primaryInputDevice |
P2571
|
FINISHED |
| Object | mouse |
—
|
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: mouse | Statement: [Apple Macintosh computers, primaryInputDevice, mouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryInputDevice Context triple: [Apple Macintosh computers, primaryInputDevice, mouse]
-
A.
inputDevice
chosen
Indicates that one entity functions as a device used to provide input to another entity or system.
-
B.
primaryMode
Indicates the main or most commonly used method, manner, or form in which an action, process, or interaction is carried out between entities.
-
C.
userInterface
Indicates a relationship where one entity serves as the interface or interaction layer through which a user engages with another system, service, or resource.
-
D.
primaryTarget
Indicates that an entity is the main or most important target of another entity’s action, focus, or effect.
-
E.
primaryUser
Indicates that the referenced user is the main or principal user associated with a given account, resource, or context.
- 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_69a24c06b3bc8190aa4ac89026115efc |
completed | Feb. 28, 2026, 1:59 a.m. |
| NER | Named-entity recognition | batch_69a252201fa481908e30791954119c17 |
completed | Feb. 28, 2026, 2:25 a.m. |
| PD | Predicate disambiguation | batch_69a24eacfdc481909e9ff99752fd42bf |
completed | Feb. 28, 2026, 2:10 a.m. |
Created at: Feb. 28, 2026, 2:03 a.m.