Triple
T30428157
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sony FE 16-35mm f/2.8 GM |
E774089
|
entity |
| Predicate | intendedSensorSize |
P94366
|
FINISHED |
| Object | 35 mm full-frame |
—
|
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: 35 mm full-frame | Statement: [Sony FE 16-35mm f/2.8 GM, intendedSensorSize, 35 mm full-frame]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: intendedSensorSize Context triple: [Sony FE 16-35mm f/2.8 GM, intendedSensorSize, 35 mm full-frame]
-
A.
rearCameraSensorSize
Indicates the physical dimensions of the image sensor used by the device’s rear camera.
-
B.
mediaDimension
Indicates the physical or digital size, extent, or measurable properties (such as width, height, length, or duration) associated with a media item.
-
C.
viewfinderResolution
Indicates the resolution or level of detail provided by a device’s viewfinder display.
-
D.
desiredSizeIndicates
chosen
Indicates that one entity specifies or reflects the preferred or intended size of another entity.
-
E.
typicalResolution
Indicates the usual or standard level of detail or clarity at which something (such as an image, display, or representation) is normally rendered or presented.
- 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fcc4b700748190ae00b21d09c96695 |
completed | May 7, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fcb0f9d3d881908a049475182fb039 |
completed | May 7, 2026, 3:34 p.m. |
Created at: April 29, 2026, 8:06 p.m.