Triple

T21224625
Position Surface form Disambiguated ID Type / Status
Subject RFC 3551 E523057 entity
Predicate definesPayloadType P56536 FINISHED
Object QCELP
QCELP (Qualcomm Code Excited Linear Prediction) is a speech codec developed by Qualcomm, primarily used in CDMA cellular networks for efficient voice compression.
 E1473305 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: QCELP | Statement: [RFC 3551, definesPayloadType, QCELP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: QCELP
Context triple: [RFC 3551, definesPayloadType, QCELP]
  • A. MPEG-4 CELP
    MPEG-4 CELP is an audio coding algorithm that uses code-excited linear prediction to efficiently compress speech within the MPEG-4 multimedia framework.
  • B. G.728
    G.728 is an ITU-T speech codec that provides low-delay, 16 kbit/s compression for high-quality voice communication, commonly used in telephony and VoIP applications.
  • C. Speex
    Speex is an open-source, patent-free audio compression codec designed primarily for efficient, high-quality speech encoding.
  • D. G.723.1
    G.723.1 is an ITU-T audio codec standard designed for low-bit-rate voice compression, commonly used in VoIP and multimedia communication systems.
  • E. G.721
    G.721 is an ITU-T (formerly CCITT) audio coding standard that defines 32 kbit/s ADPCM compression for digital telephony.
  • 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: QCELP
Triple: [RFC 3551, definesPayloadType, QCELP]
Generated description
QCELP (Qualcomm Code Excited Linear Prediction) is a speech codec developed by Qualcomm, primarily used in CDMA cellular networks for efficient voice compression.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: QCELP
Target entity description: QCELP (Qualcomm Code Excited Linear Prediction) is a speech codec developed by Qualcomm, primarily used in CDMA cellular networks for efficient voice compression.
  • A. MPEG-4 CELP
    MPEG-4 CELP is an audio coding algorithm that uses code-excited linear prediction to efficiently compress speech within the MPEG-4 multimedia framework.
  • B. G.728
    G.728 is an ITU-T speech codec that provides low-delay, 16 kbit/s compression for high-quality voice communication, commonly used in telephony and VoIP applications.
  • C. Speex
    Speex is an open-source, patent-free audio compression codec designed primarily for efficient, high-quality speech encoding.
  • D. G.723.1
    G.723.1 is an ITU-T audio codec standard designed for low-bit-rate voice compression, commonly used in VoIP and multimedia communication systems.
  • E. G.721
    G.721 is an ITU-T (formerly CCITT) audio coding standard that defines 32 kbit/s ADPCM compression for digital telephony.
  • 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_69e0b512ad94819087942b2ed925185f completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e734aa82c4819086cef6364619b4e9 completed April 21, 2026, 8:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0986e6ca108190a08a088428817ae6 completed May 17, 2026, 9:14 a.m.
NEDg Description generation batch_6a0987dc2ba88190833f52eda39235f3 completed May 17, 2026, 9:18 a.m.
NED2 Entity disambiguation (via description) batch_6a09885d7178819093003533c7785dd8 completed May 17, 2026, 9:20 a.m.
Created at: April 16, 2026, 3:44 p.m.