Triple

T10904202
Position Surface form Disambiguated ID Type / Status
Subject Brighton Centre E257524 entity
Predicate hasSecondaryHall P55983 FINISHED
Object Hall 2
Hall 2 is a secondary event space within the Brighton Centre complex, used for conferences, exhibitions, and other public functions.
 E891919 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: Hall 2 | Statement: [Brighton Centre, hasSecondaryHall, Hall 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hall 2
Context triple: [Brighton Centre, hasSecondaryHall, Hall 2]
  • A. Hall 2
    Hall 2 is one of the exhibition and event halls within the AsiaWorld-Expo convention and exhibition center in Hong Kong.
  • B. Hall 2
    Hall 2 is one of the main concourse areas within Paris’s Gare de Lyon railway station, serving passengers with platforms, services, and amenities.
  • C. Hall 3
    Hall 3 is one of the exhibition and event halls within the AsiaWorld-Expo convention and entertainment complex in Hong Kong.
  • D. Hall 5
    Hall 5 is one of the exhibition and event halls within the AsiaWorld-Expo convention and entertainment complex in Hong Kong.
  • E. Hall 7
    Hall 7 is one of the exhibition and event halls within the AsiaWorld-Expo convention and exhibition center in Hong Kong.
  • 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: Hall 2
Triple: [Brighton Centre, hasSecondaryHall, Hall 2]
Generated description
Hall 2 is a secondary event space within the Brighton Centre complex, used for conferences, exhibitions, and other public functions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hall 2
Target entity description: Hall 2 is a secondary event space within the Brighton Centre complex, used for conferences, exhibitions, and other public functions.
  • A. Hall 2
    Hall 2 is one of the main concourse areas within Paris’s Gare de Lyon railway station, serving passengers with platforms, services, and amenities.
  • B. Hall 2
    Hall 2 is one of the exhibition and event halls within the AsiaWorld-Expo convention and exhibition center in Hong Kong.
  • C. Hall 3
    Hall 3 is one of the exhibition and event halls within the AsiaWorld-Expo convention and entertainment complex in Hong Kong.
  • D. Hall 5
    Hall 5 is one of the exhibition and event halls within the AsiaWorld-Expo convention and entertainment complex in Hong Kong.
  • E. Hall 7
    Hall 7 is one of the exhibition and event halls within the AsiaWorld-Expo convention and exhibition center in Hong Kong.
  • 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_69d6aa8550c8819095508a2ed9acf3db completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d761a5dffc8190927b0928978646a4 completed April 9, 2026, 8:21 a.m.
NED1 Entity disambiguation (via context triple) batch_69e1553bb88c8190b9730a31977e1dd1 completed April 16, 2026, 9:31 p.m.
NEDg Description generation batch_69e175e336848190b2c7226524266efa completed April 16, 2026, 11:50 p.m.
NED2 Entity disambiguation (via description) batch_69e17d46b7b881908bc3246b462f4612 completed April 17, 2026, 12:22 a.m.
Created at: April 8, 2026, 9:22 p.m.