Triple
T1291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | oN-Line System |
E25
|
entity |
| Predicate | hardwareInterface |
P35
|
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: [oN-Line System, hardwareInterface, mouse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hardwareInterface Context triple: [oN-Line System, hardwareInterface, mouse]
-
A.
isMechanicalOrElectronic
Indicates that something operates using mechanical components, electronic components, or a combination of both.
-
B.
hasPart
chosen
Indicates that one entity is a component, segment, or constituent part of another entity.
-
C.
isAnalogOrDigital
Indicates whether something operates using analog signals/representation or digital signals/representation.
-
D.
hasPrimaryFunction
Indicates that one entity serves as the main or principal function or role of another entity.
-
E.
operatesBy
Indicates that an entity performs its function, action, or process through the use or application of another entity (e.g., a method, mechanism, or principle).
- 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a23211f05c8190b8deb03a8540d84d |
completed | Feb. 28, 2026, 12:08 a.m. |
| PD | Predicate disambiguation | batch_69a230c2c48481908beb1db3cc9768aa |
completed | Feb. 28, 2026, 12:03 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.