Triple

T6398128
Position Surface form Disambiguated ID Type / Status
Subject IRCAM E143990 entity
Predicate notableWork P4 FINISHED
Object AudioSculpt
AudioSculpt is a sound analysis and processing software developed by IRCAM, widely used for detailed spectral editing and transformation of audio.
E590929 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: AudioSculpt | Statement: [IRCAM, notableWork, AudioSculpt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: AudioSculpt
Context triple: [IRCAM, notableWork, AudioSculpt]
  • A. Audion
    Audion is an early triode vacuum tube invented by Lee de Forest that enabled the amplification of electrical signals and was crucial to the development of radio and electronics.
  • B. WaveGlow
    WaveGlow is a flow-based generative neural network model for fast, high-quality text-to-speech audio synthesis.
  • C. audioOS
    audioOS is Apple’s specialized operating system designed to power and manage the features of its HomePod smart speakers.
  • D. Auto-Tune
    Auto-Tune is an audio processing technology that automatically corrects or stylizes vocal pitch, widely used in music production for both subtle tuning and distinctive robotic effects.
  • E. Audacity
    Audacity is an American garage punk band known for its energetic, lo-fi sound and association with the Southern California DIY scene.
  • 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: AudioSculpt
Triple: [IRCAM, notableWork, AudioSculpt]
Generated description
AudioSculpt is a sound analysis and processing software developed by IRCAM, widely used for detailed spectral editing and transformation of audio.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: AudioSculpt
Target entity description: AudioSculpt is a sound analysis and processing software developed by IRCAM, widely used for detailed spectral editing and transformation of audio.
  • A. Audion
    Audion is an early triode vacuum tube invented by Lee de Forest that enabled the amplification of electrical signals and was crucial to the development of radio and electronics.
  • B. WaveGlow
    WaveGlow is a flow-based generative neural network model for fast, high-quality text-to-speech audio synthesis.
  • C. audioOS
    audioOS is Apple’s specialized operating system designed to power and manage the features of its HomePod smart speakers.
  • D. Auto-Tune
    Auto-Tune is an audio processing technology that automatically corrects or stylizes vocal pitch, widely used in music production for both subtle tuning and distinctive robotic effects.
  • E. Audacity
    Audacity is an American garage punk band known for its energetic, lo-fi sound and association with the Southern California DIY scene.
  • 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_69c008dc56fc81908d43ffcc11d73bdd completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c06896d180819091548a728e903184 completed March 22, 2026, 10:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6389bd9f48190af9811cf8cee124e completed March 27, 2026, 7:58 a.m.
NEDg Description generation batch_69c63beaa5408190b4421f49634f3df1 completed March 27, 2026, 8:12 a.m.
NED2 Entity disambiguation (via description) batch_69c63c5f7d508190bd263822cea1b782 completed March 27, 2026, 8:14 a.m.
Created at: March 22, 2026, 4:35 p.m.