Triple

T1503637
Position Surface form Disambiguated ID Type / Status
Subject Tandberg E33850 entity
Predicate technology P1485 FINISHED
Object H.323
H.323 is an ITU-T standard that defines protocols for voice, video, and data communication over packet-based networks such as IP.
E171421 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: H.323 | Statement: [Tandberg, technology, H.323]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: H.323
Context triple: [Tandberg, technology, H.323]
  • A. H.248
    H.248 is an ITU-T protocol, also known as Megaco, used for controlling media gateways in next-generation and IP multimedia networks.
  • B. G.722
    G.722 is a wideband audio codec standard that provides higher-quality voice transmission than traditional narrowband codecs, commonly used in VoIP and teleconferencing applications.
  • C. G.729
    G.729 is a widely used ITU-T audio codec standard that compresses voice for bandwidth-efficient transmission in VoIP and other telephony applications.
  • D. G.711
    G.711 is a widely used ITU-T audio codec standard for pulse code modulation (PCM) of voice in traditional telephony and VoIP systems.
  • E. Tandberg
    Tandberg is a Norwegian company best known for its video conferencing and telepresence solutions, which became part of Cisco Systems after its acquisition.
  • 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: H.323
Triple: [Tandberg, technology, H.323]
Generated description
H.323 is an ITU-T standard that defines protocols for voice, video, and data communication over packet-based networks such as IP.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: H.323
Target entity description: H.323 is an ITU-T standard that defines protocols for voice, video, and data communication over packet-based networks such as IP.
  • A. H.248
    H.248 is an ITU-T protocol, also known as Megaco, used for controlling media gateways in next-generation and IP multimedia networks.
  • B. G.722
    G.722 is a wideband audio codec standard that provides higher-quality voice transmission than traditional narrowband codecs, commonly used in VoIP and teleconferencing applications.
  • C. G.729
    G.729 is a widely used ITU-T audio codec standard that compresses voice for bandwidth-efficient transmission in VoIP and other telephony applications.
  • D. G.711
    G.711 is a widely used ITU-T audio codec standard for pulse code modulation (PCM) of voice in traditional telephony and VoIP systems.
  • E. Tandberg
    Tandberg is a Norwegian company best known for its video conferencing and telepresence solutions, which became part of Cisco Systems after its acquisition.
  • 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_69a885f352a4819099b24ff15489dede completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a8872fae4c81908e7d6961e6c5fa96 completed March 4, 2026, 7:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69ad1cb578e4819082d254462e10e4f0 completed March 8, 2026, 6:52 a.m.
NEDg Description generation batch_69ad1d34656481909949b4bfd83c6142 completed March 8, 2026, 6:54 a.m.
NED2 Entity disambiguation (via description) batch_69ad1dd7b34c8190b6957be2112506dd completed March 8, 2026, 6:57 a.m.
Created at: March 4, 2026, 7:24 p.m.