Triple
T30205187
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Atari keyboard |
E767891
|
entity |
| Predicate | supportsInputLanguage |
P194011
|
FINISHED |
| Object | English (model-dependent) |
—
|
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: English (model-dependent) | Statement: [Atari keyboard, supportsInputLanguage, English (model-dependent)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsInputLanguage Context triple: [Atari keyboard, supportsInputLanguage, English (model-dependent)]
-
A.
usesLanguageSupport
Indicates that one entity makes use of language-related assistance, features, or services provided by another entity.
-
B.
isSupportedByLanguage
Indicates that something (such as a feature, format, or construct) is compatible with and can be handled or recognized by a particular language.
-
C.
supportsLanguageOverrides
Indicates that an entity allows its default behavior or settings to be modified based on specific language selections or preferences.
-
D.
usesInputMethod
Indicates that one entity employs or relies on a particular input method or mechanism to receive or process input.
-
E.
secondaryLanguageSupport
chosen
Indicates that an entity provides assistance, services, or functionality in an additional (non-primary) language.
- 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_69f2247eb0848190b4032f302d39c0d9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_6a037c876524819098545e6037d3107d |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a0379e0f3d88190a4ee7b0673f1ef90 |
completed | May 12, 2026, 7:05 p.m. |
Created at: April 29, 2026, 7:31 p.m.