Triple

T20929464
Position Surface form Disambiguated ID Type / Status
Subject No. 1 Recruit Training Unit RAAF E515429 entity
Predicate nickname P55 FINISHED
Object 1RTU
1RTU is the Royal Australian Air Force’s primary recruit training unit responsible for initial military training of new airmen and airwomen.
E1457374 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: 1RTU | Statement: [No. 1 Recruit Training Unit RAAF, nickname, 1RTU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 1RTU
Context triple: [No. 1 Recruit Training Unit RAAF, nickname, 1RTU]
  • A. RTU
    RTU was the original name of the Chilean television channel now known as Chilevisión, one of Chile’s major national broadcasters.
  • B. RTD
    RTD is the primary public transit agency serving the Denver metropolitan area in Colorado, operating buses, light rail, and commuter rail services.
  • C. RTD
    RTD was the former name of Arquus, a French manufacturer specializing in military and defense vehicles.
  • D. RTD
    RTD is the commonly used abbreviation for the ASME Rail Transportation Division, a professional group focused on rail engineering and technology within the American Society of Mechanical Engineers.
  • E. RTN
    RTN is the former stock ticker symbol for Raytheon Company, a major U.S. defense and aerospace contractor.
  • 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: 1RTU
Triple: [No. 1 Recruit Training Unit RAAF, nickname, 1RTU]
Generated description
1RTU is the Royal Australian Air Force’s primary recruit training unit responsible for initial military training of new airmen and airwomen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: 1RTU
Target entity description: 1RTU is the Royal Australian Air Force’s primary recruit training unit responsible for initial military training of new airmen and airwomen.
  • A. RTU
    RTU was the original name of the Chilean television channel now known as Chilevisión, one of Chile’s major national broadcasters.
  • B. RTD
    RTD was the former name of Arquus, a French manufacturer specializing in military and defense vehicles.
  • C. RTD
    RTD is the primary public transit agency serving the Denver metropolitan area in Colorado, operating buses, light rail, and commuter rail services.
  • D. RTD
    RTD is the commonly used abbreviation for the ASME Rail Transportation Division, a professional group focused on rail engineering and technology within the American Society of Mechanical Engineers.
  • E. RTN
    RTN is the former stock ticker symbol for Raytheon Company, a major U.S. defense and aerospace contractor.
  • 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_69e0b4fb431c8190b9d40e6a72f0cc87 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6f6545f8c81908a8c2f0e8d7b060e completed April 21, 2026, 4 a.m.
NED1 Entity disambiguation (via context triple) batch_6a091fce6b148190b2dcf07d95696744 completed May 17, 2026, 1:54 a.m.
NEDg Description generation batch_6a09206824148190881bef138312d37f completed May 17, 2026, 1:56 a.m.
NED2 Entity disambiguation (via description) batch_6a0920d752888190bffcfa7ce75cd2ad completed May 17, 2026, 1:58 a.m.
Created at: April 16, 2026, 12:49 p.m.