Triple
T7857391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Touch Cover |
E182411
|
entity |
| Predicate | keyLayout |
P79393
|
FINISHED |
| Object | full QWERTY layout |
—
|
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: full QWERTY layout | Statement: [Touch Cover, keyLayout, full QWERTY layout]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keyLayout Context triple: [Touch Cover, keyLayout, full QWERTY layout]
-
A.
keyAction
Indicates an action that is performed using a key, typically involving locking, unlocking, or otherwise operating a mechanism that requires a key.
-
B.
keyHitter
Indicates that an entity is a powerful or highly effective performer, especially in a competitive or performance-based context.
-
C.
keyState
Indicates the current status or condition of a key (such as pressed, released, locked, or unlocked) in relation to an associated object or system.
-
D.
keyboardsBy
Indicates that one entity is the creator, manufacturer, or provider of keyboards associated with another entity.
-
E.
keyThemeIn
Indicates that a particular theme is a central or primary thematic focus within a given work, context, or subject.
- 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_69ca82887fd48190975896bf38c4596b |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb1a76f8648190976b488d0d8658ef |
completed | March 31, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69cae92180f88190ae3d44c3de7adc93 |
completed | March 30, 2026, 9:20 p.m. |
| PDg | Predicate description generation | batch_69caf786ec748190b6347b0c94335550 |
completed | March 30, 2026, 10:21 p.m. |
Created at: March 30, 2026, 4:52 p.m.