Triple

T11791576
Position Surface form Disambiguated ID Type / Status
Subject Faf de Klerk E280399 entity
Predicate nickname P55 FINISHED
Object Faf
Faf is a South African rugby union scrum-half known for his dynamic playmaking, tenacious defense, and distinctive long blond hair.
 E946839 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: Faf | Statement: [Faf de Klerk, nickname, Faf]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Faf
Context triple: [Faf de Klerk, nickname, Faf]
  • A. Finidi
    Finidi is a former Nigerian professional footballer best known for his successful career as a winger with clubs like Ajax and Real Betis and for his key role in the Nigerian national team of the 1990s.
  • B. Fassel
    Fassel is a surname most notably associated with Jim Fassel, a former head coach of the New York Giants in the National Football League.
  • C. Faifi
    Faifi is a modern South Arabian language variety spoken by the Faifi people in the mountainous Jazan region of southwestern Saudi Arabia.
  • D. Malan
    Malan is a surname of Afrikaans and French Huguenot origin, notably borne by figures such as South African prime minister D. F. Malan.
  • E. Frafra
    Frafra are an ethnic group of northern Ghana, known for their Gurunsi-related language, distinctive mud architecture, and rich agricultural and craft traditions.
  • 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: Faf
Triple: [Faf de Klerk, nickname, Faf]
Generated description
Faf is a South African rugby union scrum-half known for his dynamic playmaking, tenacious defense, and distinctive long blond hair.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Faf
Target entity description: Faf is a South African rugby union scrum-half known for his dynamic playmaking, tenacious defense, and distinctive long blond hair.
  • A. Finidi
    Finidi is a former Nigerian professional footballer best known for his successful career as a winger with clubs like Ajax and Real Betis and for his key role in the Nigerian national team of the 1990s.
  • B. Fassel
    Fassel is a surname most notably associated with Jim Fassel, a former head coach of the New York Giants in the National Football League.
  • C. Faifi
    Faifi is a modern South Arabian language variety spoken by the Faifi people in the mountainous Jazan region of southwestern Saudi Arabia.
  • D. Malan
    Malan is a surname of Afrikaans and French Huguenot origin, notably borne by figures such as South African prime minister D. F. Malan.
  • E. Frafra
    Frafra are an ethnic group of northern Ghana, known for their Gurunsi-related language, distinctive mud architecture, and rich agricultural and craft traditions.
  • 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_69d6ab258b808190b1735835c841e3a4 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8a588d2c881909783c2d678c2a474 completed April 10, 2026, 7:23 a.m.
NED1 Entity disambiguation (via context triple) batch_69f09107fd2481908d765d2188035012 completed April 28, 2026, 10:50 a.m.
NEDg Description generation batch_69f0bd40108c8190863a60cf01cc7201 completed April 28, 2026, 1:59 p.m.
NED2 Entity disambiguation (via description) batch_69f0ef7e9f388190b33f6c16abadfde9 completed April 28, 2026, 5:33 p.m.
Created at: April 8, 2026, 9:42 p.m.