Triple

T15768814
Position Surface form Disambiguated ID Type / Status
Subject Twister E382294 entity
Predicate soundMix P14839 FINISHED
Object SDDS E237278 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: SDDS | Statement: [Twister, soundMix, SDDS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SDDS
Context triple: [Twister, soundMix, SDDS]
  • A. SDDS chosen
    SDDS (Sony Dynamic Digital Sound) is a multichannel digital cinema sound format developed by Sony to provide high-quality, immersive audio in movie theaters.
  • B. SDDS
    SDDS is an International Monetary Fund standard that guides countries in providing timely and comprehensive economic and financial statistics to the public and markets.
  • C. SDDS Plus
    SDDS Plus is an enhanced tier of the IMF’s data dissemination standards that requires countries to provide more comprehensive, timely, and detailed economic and financial statistics to support global financial stability and transparency.
  • D. DSD
    DSD is the former name of Australia’s national signals intelligence and information security agency, now known as the Australian Signals Directorate.
  • E. DSD
    DSD is the abbreviated name commonly used for the Data Services Department within an organization.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e051951bac8190a7d45f3612c6de72 completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff877a67008190b05f879d05876fd3 completed May 9, 2026, 7:14 p.m.
Created at: April 10, 2026, 4:47 a.m.