Triple
T326861
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | TI-89 Titanium |
E6537
|
entity |
| Predicate | hasKeyboardLayout |
P5738
|
FINISHED |
| Object | QWERTY-like alpha keys |
—
|
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: QWERTY-like alpha keys | Statement: [TI-89 Titanium, hasKeyboardLayout, QWERTY-like alpha keys]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasKeyboardLayout Context triple: [TI-89 Titanium, hasKeyboardLayout, QWERTY-like alpha keys]
-
A.
hasKeypadLayout
chosen
Indicates that one entity possesses or uses a specific arrangement or configuration of keys or buttons provided by another entity.
-
B.
hasKeyEvent
Indicates that an entity includes, is associated with, or is characterized by a significant or defining event.
-
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.
hasKeyType
Indicates that an entity possesses or is associated with a specific category or type of key.
-
E.
hasInputType
Indicates that an entity takes another entity as its input type for its operation, function, or process.
- 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_69a2e7933d6c8190bb2592ad13286ef2 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2ea974d8481908c7d84f72a7728b6 |
completed | Feb. 28, 2026, 1:16 p.m. |
| PD | Predicate disambiguation | batch_69a2e94aab1c8190b8654708c87eeb91 |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.