Triple

T28611166
Position Surface form Disambiguated ID Type / Status
Subject SDL E724169 entity
Predicate supportsAudioBackend P168762 FINISHED
Object DirectSound
DirectSound is a legacy Microsoft Windows audio API that provides low-latency playback and mixing of sound for games and multimedia applications.
 E37364 NE FINISHED

How this triple was built (3 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: DirectSound | Statement: [SDL, supportsAudioBackend, DirectSound]
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: DirectSound
Triple: [SDL, supportsAudioBackend, DirectSound]
Generated description
DirectSound is a legacy Microsoft Windows audio API that provides low-latency playback and mixing of sound for games and multimedia applications.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: supportsAudioBackend
Context triple: [SDL, supportsAudioBackend, DirectSound]
  • A. audioBackend chosen
    Indicates the audio processing or playback system used to handle sound for a given entity or context.
  • B. audioFormatSupported
    Indicates that a particular audio format is recognized and can be correctly processed or played by a given system or component.
  • C. supportsAudioAssociation
    Indicates that one entity can be linked with or is capable of maintaining an association to an audio resource or audio-related data.
  • D. supportsAudioReturnChannel
    Indicates that one entity is capable of handling an audio return channel from another entity, allowing audio to be sent back over the same connection.
  • E. hasAudioFeature
    Indicates that one entity possesses or is associated with a specific audio-related characteristic or property.
  • F. None of above.

Provenance (6 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_69f01d816d7c8190a1fe27e3434041dc completed April 28, 2026, 2:37 a.m.
NER Named-entity recognition batch_6a01487b73488190954eb5143e6f246e completed May 11, 2026, 3:09 a.m.
NED1 Entity disambiguation (via context triple) batch_6a1cc375a6a081908aac64f94ec94f4a completed May 31, 2026, 11:25 p.m.
NEDg Description generation batch_6a1cc4088b408190b5ad487fcdfac2ac completed May 31, 2026, 11:28 p.m.
NED2 Entity disambiguation (via description) batch_6a1cc4b69e5c8190bae7beb6a8b82aa7 completed May 31, 2026, 11:31 p.m.
PD Predicate disambiguation batch_6a0145210ae481908da59b02efdbc397 completed May 11, 2026, 2:55 a.m.
Created at: April 28, 2026, 4:30 a.m.