Triple

T9002134
Position Surface form Disambiguated ID Type / Status
Subject VC-1 E215061 entity
Predicate basedOn P98 FINISHED
Object Windows Media Video 9 E193862 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: Windows Media Video 9 | Statement: [VC-1, basedOn, Windows Media Video 9]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Windows Media Video 9
Context triple: [VC-1, basedOn, Windows Media Video 9]
  • A. Video for Windows
    Video for Windows is an early Microsoft multimedia framework and API for Windows that enabled digital video playback and editing on PCs in the 1990s.
  • B. WMV chosen
    WMV (Windows Media Video) is a series of Microsoft-developed video compression formats commonly used for streaming and storing digital video on Windows platforms.
  • C. DivX
    DivX is a proprietary video codec and software suite known for enabling high-quality video compression suitable for digital distribution and playback.
  • D. MPEG-4
    MPEG-4 is a multimedia compression and coding standard widely used for digital audio, video, and interactive media distribution over the internet and other networks.
  • E. Windows Media
    Windows Media is a collection of Microsoft multimedia technologies and formats used for playing, streaming, and encoding audio and video on Windows platforms.
  • 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_69ca83a12d648190b1e4fe11e8a31890 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc6956a6e08190bd3853a7c1c130eb completed April 1, 2026, 12:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfd0ddb1648190a50f8877218d9883 completed April 3, 2026, 2:38 p.m.
Created at: March 30, 2026, 7:05 p.m.