Triple

T22332094
Position Surface form Disambiguated ID Type / Status
Subject University of the North E552047 entity
Predicate alsoKnownAs P39 FINISHED
Object Turfloop
Turfloop is the commonly used name for the University of the North, a historically significant South African university located near Polokwane in Limpopo province.
 E1531433 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: Turfloop | Statement: [University of the North, alsoKnownAs, Turfloop]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Turfloop
Context triple: [University of the North, alsoKnownAs, Turfloop]
  • A. Soweto Derby
    The Soweto Derby is one of South Africa’s most famous and fiercely contested football rivalries, played between Johannesburg giants Kaizer Chiefs and Orlando Pirates.
  • B. Turf
    "Turf" is a song by the American indie pop band Good for You.
  • C. Soweto Highway
    Soweto Highway is a major roadway in Johannesburg, South Africa, that connects the city to the township of Soweto and serves as a key commuter and event access route.
  • D. Koppies
    Koppies is a small town in South Africa’s Free State province, known for its surrounding agricultural lands and proximity to the Koppies Dam and nature reserve.
  • E. Turf War
    Turf War is the signature multiplayer mode in the Splatoon series where teams compete to cover the most ground with their ink.
  • 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: Turfloop
Triple: [University of the North, alsoKnownAs, Turfloop]
Generated description
Turfloop is the commonly used name for the University of the North, a historically significant South African university located near Polokwane in Limpopo province.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Turfloop
Target entity description: Turfloop is the commonly used name for the University of the North, a historically significant South African university located near Polokwane in Limpopo province.
  • A. Soweto Derby
    The Soweto Derby is one of South Africa’s most famous and fiercely contested football rivalries, played between Johannesburg giants Kaizer Chiefs and Orlando Pirates.
  • B. Turf
    "Turf" is a song by the American indie pop band Good for You.
  • C. Soweto Highway
    Soweto Highway is a major roadway in Johannesburg, South Africa, that connects the city to the township of Soweto and serves as a key commuter and event access route.
  • D. Koppies
    Koppies is a small town in South Africa’s Free State province, known for its surrounding agricultural lands and proximity to the Koppies Dam and nature reserve.
  • E. Turf War
    Turf War is the signature multiplayer mode in the Splatoon series where teams compete to cover the most ground with their ink.
  • 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_69e11e482f788190b78d1588fc26d606 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f1577b555c8190ac61c026ee7dfb2b completed April 29, 2026, 12:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0ad526a268819084cd7df7d7de1a23 completed May 18, 2026, 9 a.m.
NEDg Description generation batch_6a0ad992b43c8190b0e409d64db83308 completed May 18, 2026, 9:19 a.m.
NED2 Entity disambiguation (via description) batch_6a0adac48bec8190989dd7c5e28d283a completed May 18, 2026, 9:24 a.m.
Created at: April 16, 2026, 8:43 p.m.