Triple

T425485
Position Surface form Disambiguated ID Type / Status
Subject Apple M2 E8197 entity
Predicate supportsVideoCodec P203 FINISHED
Object ProRes RAW E53639 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: ProRes RAW | Statement: [Apple M2, supportsVideoCodec, ProRes RAW]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ProRes RAW
Context triple: [Apple M2, supportsVideoCodec, ProRes RAW]
  • A. ProRes chosen
    ProRes is a high-quality, high-performance video compression format developed by Apple and widely used in professional video production and post‑production workflows.
  • B. H.264
    H.264 is a widely used video compression standard known for delivering high-quality video at relatively low bitrates, commonly employed in streaming, broadcasting, and video recording.
  • C. TIFF
    TIFF is the non-profit cultural organization that runs the Toronto International Film Festival and related year-round film programs and events.
  • D. SMPTE ST 2022
    SMPTE ST 2022 is a family of standards from the Society of Motion Picture and Television Engineers that defines the transport of professional audio, video, and ancillary data over IP networks, including methods for encapsulation, error correction, and redundancy.
  • E. SMPTE ST 2059
    SMPTE ST 2059 is a professional media industry standard that defines how to use IEEE 1588 Precision Time Protocol to synchronize clocks and signals across IP-based audio, video, and broadcast systems.
  • 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_69a2e7f1d1bc81909cf2dc9754a3c334 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2f01be4108190b4c13346afd95a03 completed Feb. 28, 2026, 1:39 p.m.
NED1 Entity disambiguation (via context triple) batch_69a42f665c2881908850bce36cdf74b8 completed March 1, 2026, 12:21 p.m.
Created at: Feb. 28, 2026, 1:11 p.m.