Triple
T38619594
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blackmagic URSA Broadcast G2 |
E936831
|
entity |
| Predicate | supportsTimecode |
P99409
|
FINISHED |
| Object | timecode input |
—
|
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: timecode input | Statement: [Blackmagic URSA Broadcast G2, supportsTimecode, timecode input]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: supportsTimecode Context triple: [Blackmagic URSA Broadcast G2, supportsTimecode, timecode input]
-
A.
supportsTimecodes
chosen
Indicates that one entity can handle, interpret, or work with timecode information associated with another entity or data stream.
-
B.
supportsProResVideo
Indicates that one entity provides the capability for another entity to record, process, or handle video in the ProRes format.
-
C.
supportsTimescale
Indicates that one entity is capable of operating with, accommodating, or being compatible with a specified timescale or range of temporal resolutions.
-
D.
supportsTimeStretch
Indicates that one entity provides the capability to alter the duration of another entity (such as audio or video) without changing its pitch.
-
E.
supportsProResEncodeDecode
Indicates that an entity provides the capability to both encode and decode media using the Apple ProRes format.
- 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_6a037c9141dc819098d7fcc36e69882c |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a2026248190b894436a578d79ac |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:32 p.m.