Triple
T10170455
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ProRes RAW |
E235316
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Apple ProRes |
E53639
|
NE 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: Apple ProRes | Statement: [ProRes RAW, partOf, Apple ProRes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apple ProRes Context triple: [ProRes RAW, partOf, Apple ProRes]
-
A.
ProRes
chosen
ProRes is a high-quality, high-performance video compression format developed by Apple and widely used in professional video production and post‑production workflows.
-
B.
ProRes RAW
ProRes RAW is a high-quality, compressed raw video codec developed by Apple that combines the flexibility of raw image data with the performance and efficiency of the ProRes format for professional video production.
-
C.
XAVC HS
XAVC HS is a high-efficiency 4K/8K video recording format from Sony based on H.265/HEVC compression, designed to deliver high image quality at relatively low bitrates.
-
D.
DNxHD
DNxHD is a high-definition video codec developed by Avid, widely used in professional post-production for high-quality, edit-friendly media.
-
E.
DNxHR
DNxHR is a high-quality, high-resolution post-production video codec developed by Avid, designed for efficient editing and finishing of HD to 4K+ media.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ca84ceafd0819085828600e11bed6b |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdec9d36608190be78665cc3410cf2 |
completed | April 2, 2026, 4:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d300f7aafc8190be874efc755bd188 |
completed | April 6, 2026, 12:40 a.m. |
Created at: March 30, 2026, 9:10 p.m.