Triple

T11352315
Position Surface form Disambiguated ID Type / Status
Subject Matroska E268865 entity
Predicate typicalAudioCodec P82556 FINISHED
Object Vorbis
Vorbis is an open, patent-free audio compression format known for providing high-quality sound at relatively low bitrates.
 E920743 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: Vorbis | Statement: [Matroska, typicalAudioCodec, Vorbis]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Vorbis
Context triple: [Matroska, typicalAudioCodec, Vorbis]
  • A. Vorbis
    Vorbis is a fanatical and manipulative high priest and inquisitor who serves as the primary antagonist in Terry Pratchett’s Discworld novel "Small Gods."
  • B. WavPack
    WavPack is a free, open-source audio compression format known for offering both lossless and hybrid (lossy+correction) encoding modes.
  • C. Indeo
    Indeo is a family of video codecs developed by Intel that was widely used in the 1990s for compressed digital video playback on personal computers.
  • D. Monkey's Audio
    Monkey's Audio is a lossless audio compression format and codec known for its high compression ratios and Windows-focused software tools.
  • E. MPEG-1 Audio Layer III
    MPEG-1 Audio Layer III, commonly known as MP3, is a widely used digital audio encoding format that compresses sound data to significantly reduce file size while maintaining acceptable sound quality.
  • 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: Vorbis
Triple: [Matroska, typicalAudioCodec, Vorbis]
Generated description
Vorbis is an open, patent-free audio compression format known for providing high-quality sound at relatively low bitrates.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Vorbis
Target entity description: Vorbis is an open, patent-free audio compression format known for providing high-quality sound at relatively low bitrates.
  • A. Vorbis
    Vorbis is a fanatical and manipulative high priest and inquisitor who serves as the primary antagonist in Terry Pratchett’s Discworld novel "Small Gods."
  • B. WavPack
    WavPack is a free, open-source audio compression format known for offering both lossless and hybrid (lossy+correction) encoding modes.
  • C. Indeo
    Indeo is a family of video codecs developed by Intel that was widely used in the 1990s for compressed digital video playback on personal computers.
  • D. Monkey's Audio
    Monkey's Audio is a lossless audio compression format and codec known for its high compression ratios and Windows-focused software tools.
  • E. MPEG-1 Audio Layer III
    MPEG-1 Audio Layer III, commonly known as MP3, is a widely used digital audio encoding format that compresses sound data to significantly reduce file size while maintaining acceptable sound quality.
  • 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_69d6aacbe18081909e5fadb50082dd96 completed April 8, 2026, 7:21 p.m.
NER Named-entity recognition batch_69d808855a7481909314f90ad92aae68 completed April 9, 2026, 8:13 p.m.
NED1 Entity disambiguation (via context triple) batch_69e543a6e97481909dc77a553b217b4d completed April 19, 2026, 9:05 p.m.
NEDg Description generation batch_69e548bb7be4819093aeeaf0c048033e completed April 19, 2026, 9:27 p.m.
NED2 Entity disambiguation (via description) batch_69e54efda820819092d6a94fa4fd21f0 completed April 19, 2026, 9:54 p.m.
Created at: April 8, 2026, 9:33 p.m.