Triple

T3078568
Position Surface form Disambiguated ID Type / Status
Subject Dolby Digital E64199 entity
Predicate alsoKnownAs P39 FINISHED
Object AC-3
AC-3 is a multichannel digital audio compression format developed by Dolby Laboratories, widely used for surround sound in cinema, DVD, and broadcast applications.
 E324963 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: AC-3 | Statement: [Dolby Digital, alsoKnownAs, AC-3]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: AC-3
Context triple: [Dolby Digital, alsoKnownAs, AC-3]
  • A. ACO
    ACO is the commonly used abbreviation for Allied Command Operations, one of NATO’s two strategic military commands responsible for planning and executing alliance operations.
  • B. ACE
    ACE (Altamont Corridor Express) is a commuter rail service in California’s San Joaquin Valley and East Bay that provides weekday trains between Stockton and San Jose.
  • C. ACE
    ACE is the commonly used acronym for Arts Council England, the national body that supports and funds arts and culture across England.
  • D. ACE
    ACE is the IATA airport code for Lanzarote Airport in Spain’s Canary Islands.
  • E. ACE
    ACE is a Canadian satellite mission focused on studying Earth's atmosphere and climate through detailed measurements of atmospheric chemistry.
  • 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: AC-3
Triple: [Dolby Digital, alsoKnownAs, AC-3]
Generated description
AC-3 is a multichannel digital audio compression format developed by Dolby Laboratories, widely used for surround sound in cinema, DVD, and broadcast applications.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: AC-3
Target entity description: AC-3 is a multichannel digital audio compression format developed by Dolby Laboratories, widely used for surround sound in cinema, DVD, and broadcast applications.
  • A. ACO
    ACO is the commonly used abbreviation for Allied Command Operations, one of NATO’s two strategic military commands responsible for planning and executing alliance operations.
  • B. ACE
    ACE (Altamont Corridor Express) is a commuter rail service in California’s San Joaquin Valley and East Bay that provides weekday trains between Stockton and San Jose.
  • C. ACE
    ACE is the commonly used acronym for Arts Council England, the national body that supports and funds arts and culture across England.
  • D. ACE
    ACE is the IATA airport code for Lanzarote Airport in Spain’s Canary Islands.
  • E. ACE
    ACE is a Canadian satellite mission focused on studying Earth's atmosphere and climate through detailed measurements of atmospheric chemistry.
  • 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_69ad857bb4c88190a4cf27893fcabed8 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada1a86a848190a47ca127cc7e6326 completed March 8, 2026, 4:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1f890a21c8190bcb78fe5c9ec6e75 completed March 11, 2026, 11:19 p.m.
NEDg Description generation batch_69b1f9883fa48190b41921bcfbe55e59 completed March 11, 2026, 11:23 p.m.
NED2 Entity disambiguation (via description) batch_69b1f9f759408190a4f2121078fe13cb completed March 11, 2026, 11:25 p.m.
Created at: March 8, 2026, 3:02 p.m.