Triple
T7279479
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Intel Quick Sync Video |
E163109
|
entity |
| Predicate | supportedBy |
P67
|
FINISHED |
| Object |
OBS Studio
OBS Studio is a free, open-source software application for video recording and live streaming widely used by gamers, content creators, and professionals.
|
E653482
|
NE FINISHED |
How this triple was built (4 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: OBS Studio | Statement: [Intel Quick Sync Video, supportedBy, OBS Studio]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: OBS Studio Context triple: [Intel Quick Sync Video, supportedBy, OBS Studio]
-
A.
DaVinci Resolve
DaVinci Resolve is a professional video editing, color grading, visual effects, and audio post-production software suite widely used in film and television.
-
B.
VLC
VLC is the three-letter IATA airport code assigned to Valencia Airport in Spain.
-
C.
Wistia
Wistia is a video hosting and marketing platform focused on helping businesses create, manage, and analyze video content for sales and marketing.
-
D.
Lightworks
Lightworks is a track by the experimental hip-hop producer Donuts, known for its intricate sampling and innovative beat construction.
-
E.
Adobe Media Encoder
Adobe Media Encoder is a video and audio transcoding application from Adobe that lets users export, compress, and convert media into various formats for playback, broadcast, and online distribution.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: OBS Studio Triple: [Intel Quick Sync Video, supportedBy, OBS Studio]
Generated description
OBS Studio is a free, open-source software application for video recording and live streaming widely used by gamers, content creators, and professionals.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: OBS Studio Target entity description: OBS Studio is a free, open-source software application for video recording and live streaming widely used by gamers, content creators, and professionals.
-
A.
DaVinci Resolve
DaVinci Resolve is a professional video editing, color grading, visual effects, and audio post-production software suite widely used in film and television.
-
B.
VLC
VLC is the three-letter IATA airport code assigned to Valencia Airport in Spain.
-
C.
Wistia
Wistia is a video hosting and marketing platform focused on helping businesses create, manage, and analyze video content for sales and marketing.
-
D.
Lightworks
Lightworks is a track by the experimental hip-hop producer Donuts, known for its intricate sampling and innovative beat construction.
-
E.
Adobe Media Encoder
Adobe Media Encoder is a video and audio transcoding application from Adobe that lets users export, compress, and convert media into various formats for playback, broadcast, and online distribution.
- F. None of above. chosen
Provenance (5 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_69c6885c5964819085b209701769877f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6eb339b1081909f648864e210f98e |
completed | March 27, 2026, 8:40 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7db3450208190b67e4329a531ad0c |
completed | March 28, 2026, 1:44 p.m. |
| NEDg | Description generation | batch_69c7dc567004819089c6c4b5322f275f |
completed | March 28, 2026, 1:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7dd18f8d481908bd7ac86e4388ce5 |
completed | March 28, 2026, 1:52 p.m. |
Created at: March 27, 2026, 2:59 p.m.