Triple

T1082267
Position Surface form Disambiguated ID Type / Status
Subject Constitutional Court of South Africa E23971 entity
Predicate abbreviation P43 FINISHED
Object ConCourt
ConCourt is the highest court in South Africa on constitutional matters, renowned for safeguarding the country’s constitutional democracy and human rights.
E125166 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: ConCourt | Statement: [Constitutional Court of South Africa, abbreviation, ConCourt]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ConCourt
Context triple: [Constitutional Court of South Africa, abbreviation, ConCourt]
  • A. Front Court
    Front Court is the historic main courtyard of Emmanuel College, Cambridge, forming the central architectural and social focus of the college.
  • B. Front Court
    Front Court is the historic main quadrangle of King's College, Cambridge, known for its iconic collegiate architecture and central role in college life.
  • C. The Hoops
    The Hoops is a common nickname for FC Dallas, a professional Major League Soccer club based in the Dallas–Fort Worth metroplex.
  • D. Corte
    Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
  • E. COUR
    COUR is the stock ticker symbol for Coursera, a major online learning platform offering courses, certificates, and degrees from universities and companies worldwide.
  • 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: ConCourt
Triple: [Constitutional Court of South Africa, abbreviation, ConCourt]
Generated description
ConCourt is the highest court in South Africa on constitutional matters, renowned for safeguarding the country’s constitutional democracy and human rights.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ConCourt
Target entity description: ConCourt is the highest court in South Africa on constitutional matters, renowned for safeguarding the country’s constitutional democracy and human rights.
  • A. Front Court
    Front Court is the historic main courtyard of Emmanuel College, Cambridge, forming the central architectural and social focus of the college.
  • B. Front Court
    Front Court is the historic main quadrangle of King's College, Cambridge, known for its iconic collegiate architecture and central role in college life.
  • C. The Hoops
    The Hoops is a common nickname for FC Dallas, a professional Major League Soccer club based in the Dallas–Fort Worth metroplex.
  • D. Corte
    Corte is a historic inland town in central Corsica known for its dramatic citadel and role as a former capital of the island.
  • E. COUR
    COUR is the stock ticker symbol for Coursera, a major online learning platform offering courses, certificates, and degrees from universities and companies worldwide.
  • 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_69a493f1ddf48190a99d54b00e99f8ce completed March 1, 2026, 7:30 p.m.
NER Named-entity recognition batch_69a4b95d35888190a20593a278175df7 completed March 1, 2026, 10:10 p.m.
NED1 Entity disambiguation (via context triple) batch_69ac42affbac8190b6b16a1d726d0d35 completed March 7, 2026, 3:22 p.m.
NEDg Description generation batch_69ac44a7a69c8190af5289f6e46d571a completed March 7, 2026, 3:30 p.m.
NED2 Entity disambiguation (via description) batch_69ac451af1508190a55c037328b41931 completed March 7, 2026, 3:32 p.m.
Created at: March 1, 2026, 7:42 p.m.