Triple

T21015481
Position Surface form Disambiguated ID Type / Status
Subject Belle Vue E517661 entity
Predicate hasStand P6313 FINISHED
Object East Stand
East Stand is a spectator seating section at the Belle Vue stadium, providing views of the playing field from the eastern side of the ground.
 E1462511 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: East Stand | Statement: [Belle Vue, hasStand, East Stand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: East Stand
Context triple: [Belle Vue, hasStand, East Stand]
  • A. East Stand
    The East Stand is one of the main spectator stands at Old Trafford stadium, providing seating and facilities for fans watching Manchester United home matches.
  • B. East Stand
    East Stand is a spectator seating section within Parc y Scarlets stadium, providing views of the pitch for rugby and other events.
  • C. East Stand
    The East Stand was one of the main spectator stands at Tottenham Hotspur’s former home ground, White Hart Lane, providing seating and facilities for fans along the side of the pitch.
  • D. East Stand
    East Stand is a spectator seating section of King Power Stadium, home of Leicester City Football Club.
  • E. East Stand
    East Stand is a spectator stand within Sunderland A.F.C.’s Stadium of Light, providing seating and facilities for fans along one side of the football ground.
  • 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: East Stand
Triple: [Belle Vue, hasStand, East Stand]
Generated description
East Stand is a spectator seating section at the Belle Vue stadium, providing views of the playing field from the eastern side of the ground.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: East Stand
Target entity description: East Stand is a spectator seating section at the Belle Vue stadium, providing views of the playing field from the eastern side of the ground.
  • A. East Stand
    East Stand is a spectator seating section of Keepmoat Stadium, providing views of the pitch and hosting fans during events.
  • B. East Stand
    East Stand is a spectator seating section at Rugby Park stadium, providing views of the pitch from the eastern side.
  • C. East Stand
    East Stand is a spectator seating section of the Kingston Communications Stadium, providing views of the pitch from the eastern side of the venue.
  • D. East Stand
    East Stand is a spectator seating section of the Reebok Stadium, providing views along one side of the football ground.
  • E. East Stand
    East Stand is a spectator seating section of Kings Park Stadium, providing views of the playing field from the eastern side of the venue.
  • 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_69e0b50262b081909bc488937145eb73 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc58272881908a61eda7755ed332 completed April 21, 2026, 4:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b6544ec8190baa55bb07941a231 completed May 17, 2026, 3:52 a.m.
NEDg Description generation batch_6a093f659a7c8190a10c41821dafacc4 completed May 17, 2026, 4:09 a.m.
NED2 Entity disambiguation (via description) batch_6a0940e3b7988190b5400d16211aefcc completed May 17, 2026, 4:15 a.m.
Created at: April 16, 2026, 1:54 p.m.