Triple
T20003060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | iPad Pro 10.5-inch |
E494383
|
entity |
| Predicate | refreshRateHz |
P17633
|
FINISHED |
| Object | 120 |
—
|
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: 120 | Statement: [iPad Pro 10.5-inch, refreshRateHz, 120]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: refreshRateHz Context triple: [iPad Pro 10.5-inch, refreshRateHz, 120]
-
A.
displayRefreshRate
chosen
Indicates the frequency at which a display updates its visual content, typically measured in hertz (Hz).
-
B.
commonFrameRate
Indicates that two or more media items share the same frame rate.
-
C.
displayFrequency
Indicates how often something is shown or presented within a given context or time period.
-
D.
supportsVariableRefreshRate
Indicates that one entity provides compatibility with or functionality for dynamically adjusting refresh rates in coordination with another entity.
-
E.
referenceRate
Indicates that one entity serves as the benchmark or base rate used to determine or adjust the rate applied to another entity or transaction.
- 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_69da626b2d748190886981ea90c8b2ea |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e661a2e34481908a495cc5d077c41f |
completed | April 20, 2026, 5:25 p.m. |
| PD | Predicate disambiguation | batch_69e54cdddbd48190becc8b2aa5ab4ef9 |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 3:33 p.m.