Triple

T1666748
Position Surface form Disambiguated ID Type / Status
Subject Loftus Versfeld Stadium E36028 entity
Predicate hasStand P6313 FINISHED
Object North Stand
North Stand is a spectator seating section within Loftus Versfeld Stadium in Pretoria, South Africa, used for viewing rugby and football matches.
E188608 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: North Stand | Statement: [Loftus Versfeld Stadium, hasStand, North Stand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: North Stand
Context triple: [Loftus Versfeld Stadium, hasStand, North Stand]
  • A. North Stand
    North Stand is a spectator seating section within the City of Manchester Stadium, home of Manchester City Football Club.
  • B. North Stand
    North Stand was a spectator stand at Maine Road, the former home stadium of Manchester City Football Club.
  • C. North Stand
    North Stand is a spectator seating section at East End Park, the home stadium of Dunfermline Athletic Football Club in Scotland.
  • D. North Stand
    The North Stand is one of the main spectator sections of Dublin’s Aviva Stadium, providing tiered seating behind one of the goals for rugby and football matches.
  • E. West Stand
    West Stand is one of the main spectator stands in Dublin’s Aviva Stadium, providing seating and facilities for fans during sports and entertainment events.
  • 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: North Stand
Triple: [Loftus Versfeld Stadium, hasStand, North Stand]
Generated description
North Stand is a spectator seating section within Loftus Versfeld Stadium in Pretoria, South Africa, used for viewing rugby and football matches.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: North Stand
Target entity description: North Stand is a spectator seating section within Loftus Versfeld Stadium in Pretoria, South Africa, used for viewing rugby and football matches.
  • A. North Stand
    North Stand is a spectator seating section within the City of Manchester Stadium, home of Manchester City Football Club.
  • B. North Stand
    North Stand was a spectator stand at Maine Road, the former home stadium of Manchester City Football Club.
  • C. North Stand
    North Stand is a spectator seating section at East End Park, the home stadium of Dunfermline Athletic Football Club in Scotland.
  • D. North Stand
    The North Stand is one of the main spectator sections of Dublin’s Aviva Stadium, providing tiered seating behind one of the goals for rugby and football matches.
  • E. West Stand
    West Stand is one of the main spectator stands in Dublin’s Aviva Stadium, providing seating and facilities for fans during sports and entertainment events.
  • 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_69a8861286808190939afff3ce8ee31e completed March 4, 2026, 7:20 p.m.
NER Named-entity recognition batch_69a90adc57cc8190b270004c363768e3 completed March 5, 2026, 4:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69ad682fd42881908ecd0f331e81aba8 completed March 8, 2026, 12:14 p.m.
NEDg Description generation batch_69ad69c8af5481909d73d90e1dcaf560 completed March 8, 2026, 12:21 p.m.
NED2 Entity disambiguation (via description) batch_69ad6a4aebb88190a27350216add031b completed March 8, 2026, 12:23 p.m.
Created at: March 4, 2026, 7:29 p.m.