Triple

T18599493
Position Surface form Disambiguated ID Type / Status
Subject Cricket South Africa E454579 entity
Predicate alsoKnownAs P39 FINISHED
Object CSA
CSA is the governing body responsible for organizing and overseeing professional and amateur cricket in South Africa.
E1333442 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: CSA | Statement: [Cricket South Africa, alsoKnownAs, CSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: CSA
Context triple: [Cricket South Africa, alsoKnownAs, CSA]
  • A. CSA
    CSA is the common abbreviation for the Controlled Substances Act, the primary U.S. federal law regulating the manufacture, distribution, and use of certain drugs and chemicals.
  • B. CSA
    CSA is the College Squash Association, the governing body that oversees intercollegiate squash competition and regulations in the United States.
  • C. CSA
    CSA is the abbreviation for the Connectivity Standards Alliance, an industry consortium that develops and promotes open standards for smart home and Internet of Things devices, including the Matter protocol.
  • D. CSA
    CSA is the commonly used abbreviation for the Saginaw–Midland–Bay City Combined Statistical Area in Michigan, United States.
  • E. CSA
    CSA is an abbreviation that commonly stands for the Combined Statistical Area encompassing the Fayetteville, Lumberton, and Laurinburg regions.
  • 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: CSA
Triple: [Cricket South Africa, alsoKnownAs, CSA]
Generated description
CSA is the governing body responsible for organizing and overseeing professional and amateur cricket in South Africa.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: CSA
Target entity description: CSA is the governing body responsible for organizing and overseeing professional and amateur cricket in South Africa.
  • A. CSA chosen
    CSA is the governing body responsible for organizing and overseeing professional and amateur cricket in South Africa.
  • B. CSA
    CSA is the Canadian Soccer Association, the national governing body responsible for overseeing soccer in Canada, including its youth and senior national teams.
  • C. CSA
    CSA is the College Squash Association, the governing body that oversees intercollegiate squash competition and regulations in the United States.
  • D. CSA
    CSA is the umbrella organization of Canada’s provincial and territorial securities regulators that coordinates and harmonizes regulation of the Canadian capital markets.
  • E. CSA
    CSA is a standards development and product certification organization best known for establishing safety and performance standards across various industries in Canada and internationally.
  • F. None of above.

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_69d8d38ae7e081908a98df1251842402 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e5474f1d548190b74408eabd396344 completed April 19, 2026, 9:21 p.m.
NED1 Entity disambiguation (via context triple) batch_6a050d6eb92c8190aa0c1f4eb0deb5cb completed May 13, 2026, 11:46 p.m.
NEDg Description generation batch_6a050e04ebd881909120edb46168fbcb completed May 13, 2026, 11:49 p.m.
NED2 Entity disambiguation (via description) batch_6a050e6112e88190a399cf58ea6c8401 completed May 13, 2026, 11:50 p.m.
Created at: April 10, 2026, 11:45 a.m.