Triple

T9740669
Position Surface form Disambiguated ID Type / Status
Subject ISO/IEC 14496-3 E236176 entity
Predicate specifies P773 FINISHED
Object Advanced Audio Coding E236174 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: Advanced Audio Coding | Statement: [ISO/IEC 14496-3, specifies, Advanced Audio Coding]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Advanced Audio Coding
Context triple: [ISO/IEC 14496-3, specifies, Advanced Audio Coding]
  • A. Advanced Audio Coding chosen
    Advanced Audio Coding is a lossy digital audio compression format designed to provide better sound quality than MP3 at similar or lower bitrates and widely used in streaming, broadcasting, and multimedia applications.
  • B. HE-AAC v2
    HE-AAC v2 is an advanced audio codec profile that combines AAC with spectral band replication and parametric stereo to deliver high-quality sound at very low bitrates, commonly used in streaming and broadcasting.
  • C. Subband Codec
    Subband Codec (SBC) is an audio compression format commonly used over Bluetooth for efficiently transmitting medium-quality stereo sound with relatively low computational complexity.
  • D. ER-AAC
    ER-AAC is an error-resilient variant of the Advanced Audio Coding (AAC) audio compression format designed to provide robust audio transmission over unreliable or lossy channels.
  • E. Speex
    Speex is an open-source, patent-free audio compression codec designed primarily for efficient, high-quality speech encoding.
  • 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_69ca84d3e24481908a476e2231123cf9 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cd9f29a5bc8190b2b391017405c71e completed April 1, 2026, 10:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1bccf62e08190ae799ee557ad1f1b completed April 5, 2026, 1:37 a.m.
Created at: March 30, 2026, 8:22 p.m.