Triple
T38619588
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blackmagic URSA Broadcast G2 |
E936831
|
entity |
| Predicate | hasViewfinderOption |
P85618
|
FINISHED |
| Object | Blackmagic URSA Viewfinder |
—
|
NE NERFINISHED |
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: Blackmagic URSA Viewfinder | Statement: [Blackmagic URSA Broadcast G2, hasViewfinderOption, Blackmagic URSA Viewfinder]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasViewfinderOption Context triple: [Blackmagic URSA Broadcast G2, hasViewfinderOption, Blackmagic URSA Viewfinder]
-
A.
viewfinderType
chosen
Indicates the type or kind of viewfinder associated with or used by an entity.
-
B.
viewfinderCoverage
Indicates the extent to which what is seen through a camera’s viewfinder matches the actual area captured in the final image.
-
C.
hasOpticalFeature
Indicates that an entity possesses a specific optical characteristic or component, such as a visual property, element, or feature related to light or vision.
-
D.
viewfinderResolution
Indicates the resolution or level of detail provided by a device’s viewfinder display.
-
E.
hasFieldOfView
Indicates that one entity possesses a visual coverage area within which it can perceive or detect other entities or regions.
- 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_69f76ed403208190b862dc795171353f |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fe00dad1708190b6522476bebb43af |
completed | May 8, 2026, 3:27 p.m. |
| PD | Predicate disambiguation | batch_69fdfc3717f48190bb50ac2919c8ef95 |
completed | May 8, 2026, 3:07 p.m. |
Created at: May 3, 2026, 4:32 p.m.