Triple

T18568401
Position Surface form Disambiguated ID Type / Status
Subject Rand Afrikaans University E453814 entity
Predicate abbreviation P43 FINISHED
Object RAU
RAU is the former Rand Afrikaans University, a South African institution of higher education that later became part of the University of Johannesburg.
E1330673 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: RAU | Statement: [Rand Afrikaans University, abbreviation, RAU]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: RAU
Context triple: [Rand Afrikaans University, abbreviation, RAU]
  • A. RAA
    RAA is the abbreviation for the Royal Australian Artillery, the artillery corps of the Australian Army responsible for providing fire support and air defense.
  • B. RA
    RA is a prestigious post-nominal title indicating membership as a Royal Academician of the Royal Academy of Arts in London.
  • C. RA
    RA is the commonly used abbreviation for Rugby Australia, the governing body for rugby union in Australia.
  • D. RA
    RA is the abbreviated name commonly used for the Radiocommunications Agency, the UK body formerly responsible for managing the radio spectrum and regulating radio communications.
  • E. RA
    RA is the abbreviated name commonly used to refer to the Residents Assembly, a representative body of local residents.
  • 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: RAU
Triple: [Rand Afrikaans University, abbreviation, RAU]
Generated description
RAU is the former Rand Afrikaans University, a South African institution of higher education that later became part of the University of Johannesburg.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: RAU
Target entity description: RAU is the former Rand Afrikaans University, a South African institution of higher education that later became part of the University of Johannesburg.
  • A. RAA
    RAA is the abbreviation for the Royal Australian Artillery, the artillery corps of the Australian Army responsible for providing fire support and air defense.
  • B. RA
    RA is a prestigious post-nominal title indicating membership as a Royal Academician of the Royal Academy of Arts in London.
  • C. RA
    RA is the abbreviated name commonly used for the Radiocommunications Agency, the UK body formerly responsible for managing the radio spectrum and regulating radio communications.
  • D. RA
    RA is the commonly used abbreviation for the Royal Regiment of Artillery, a principal artillery branch of the British Army.
  • E. RA
    RA is the abbreviated name commonly used to refer to the Residents Assembly, a representative body of local residents.
  • 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_69d8d38974308190a9174430ef256b73 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53affc3e08190b4d16b5ccb0bddbc completed April 19, 2026, 8:28 p.m.
NED1 Entity disambiguation (via context triple) batch_6a049aecd7988190aeaba90194c93f12 completed May 13, 2026, 3:38 p.m.
NEDg Description generation batch_6a049f08e2608190838c6f8dc09cfa0d completed May 13, 2026, 3:55 p.m.
NED2 Entity disambiguation (via description) batch_6a049f971c34819085b6a3acab8b3ef8 completed May 13, 2026, 3:58 p.m.
Created at: April 10, 2026, 11:43 a.m.