Triple

T17417431
Position Surface form Disambiguated ID Type / Status
Subject AV1 E423521 entity
Predicate openSourceDecoder P127371 FINISHED
Object libaom NE NERFINISHED

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: libaom | Statement: [AV1, openSourceDecoder, libaom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: libaom
Context triple: [AV1, openSourceDecoder, libaom]
  • A. libaom chosen
    libaom is the official open-source reference encoder and decoder library for the AV1 video codec developed by the Alliance for Open Media.
  • B. libvpx
    libvpx is an open-source video codec library developed by Google that provides reference implementations of the VP8 and VP9 video compression standards.
  • C. AV1
    AV1 is a royalty-free, next-generation video compression codec developed by the Alliance for Open Media to efficiently deliver high-quality video over the internet.
  • D. rav1e
    rav1e is a fast, safe, and efficient Rust-based encoder for the AV1 video codec, developed as an open-source project focused on performance and reliability.
  • E. SVT-AV1
    SVT-AV1 is a high-performance, scalable open-source encoder implementation of the AV1 video compression standard, designed for efficient encoding across a wide range of hardware and use cases.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d889d7d27c819088486ce3f0627fa1 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44233c7888190a4d2aa703b206851 completed April 19, 2026, 2:47 a.m.
Created at: April 10, 2026, 5:46 a.m.