Triple
T1774691
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Commodore Amiga 1000 |
E38950
|
entity |
| Predicate | caseFeature |
P7153
|
FINISHED |
| Object | keyboard stores under case |
—
|
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: keyboard stores under case | Statement: [Commodore Amiga 1000, caseFeature, keyboard stores under case]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: caseFeature Context triple: [Commodore Amiga 1000, caseFeature, keyboard stores under case]
-
A.
letterCase
Indicates the relationship between a character or string and its typographical case (such as uppercase, lowercase, or mixed case).
-
B.
hasCase
Indicates that one entity is involved in, associated with, or characterized by a particular case, instance, or occurrence represented by another entity.
-
C.
usesCaseHarmony
Indicates that one element selects or governs another element such that their grammatical cases are compatible or harmonized according to the language’s case system.
-
D.
caseSensitivityVariant
Indicates that one string or textual form is a variant of another that differs only in letter casing (e.g., uppercase vs lowercase).
-
E.
keyFeature
chosen
Indicates that something is a primary, distinguishing, or most important feature of an entity.
- 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_69a8862e61708190af97b9838cc3f5de |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69ab17e368048190b7b73d156400f772 |
completed | March 6, 2026, 6:07 p.m. |
| PD | Predicate disambiguation | batch_69aa61cd4c1c8190a8dff391f5642bfe |
completed | March 6, 2026, 5:10 a.m. |
Created at: March 4, 2026, 7:31 p.m.