Triple

T2822973
Position Surface form Disambiguated ID Type / Status
Subject University of Johannesburg E54852 entity
Predicate abbreviation P43 FINISHED
Object UJ
UJ is a major public university in Johannesburg, South Africa, known for its diverse academic programs and strong focus on research and innovation.
 E301047 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: UJ | Statement: [University of Johannesburg, abbreviation, UJ]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UJ
Context triple: [University of Johannesburg, abbreviation, UJ]
  • A. UJC
    UJC is the youth wing of Cuba’s Communist Party, responsible for engaging and organizing young people in support of the country’s socialist project.
  • B. UzK
    UzK is the commonly used abbreviation for the University of Cologne, one of Germany’s largest and oldest universities.
  • C. UZ
    UZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Uzbekistan.
  • D. Jusos
    Jusos is the youth organization of Germany’s Social Democratic Party (SPD), representing and mobilizing young social democrats in politics and society.
  • E. the U
    The U is a common nickname for the University of Utah, a major public research university located in Salt Lake City.
  • 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: UJ
Triple: [University of Johannesburg, abbreviation, UJ]
Generated description
UJ is a major public university in Johannesburg, South Africa, known for its diverse academic programs and strong focus on research and innovation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UJ
Target entity description: UJ is a major public university in Johannesburg, South Africa, known for its diverse academic programs and strong focus on research and innovation.
  • A. UJC
    UJC is the youth wing of Cuba’s Communist Party, responsible for engaging and organizing young people in support of the country’s socialist project.
  • B. UzK
    UzK is the commonly used abbreviation for the University of Cologne, one of Germany’s largest and oldest universities.
  • C. UZ
    UZ is the two-letter ISO 3166-1 alpha-2 country code assigned to Uzbekistan.
  • D. Jusos
    Jusos is the youth organization of Germany’s Social Democratic Party (SPD), representing and mobilizing young social democrats in politics and society.
  • E. the U
    The U is a common nickname for the University of Utah, a major public research university located in Salt Lake City.
  • 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_69ab49e100c0819082a40cb797383243 completed March 6, 2026, 9:40 p.m.
NER Named-entity recognition batch_69abde71fdc08190b18660261fe24adf completed March 7, 2026, 8:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69afceaa45e88190a9007885cf7868ef completed March 10, 2026, 7:56 a.m.
NEDg Description generation batch_69afcf138c00819087913972df96f5ad completed March 10, 2026, 7:58 a.m.
NED2 Entity disambiguation (via description) batch_69afcf8d0318819088f9abd895f8ba0a completed March 10, 2026, 8 a.m.
Created at: March 6, 2026, 9:59 p.m.