Triple

T6250194
Position Surface form Disambiguated ID Type / Status
Subject Bangabandhu National Stadium E140025 entity
Predicate alsoKnownAs P39 FINISHED
Object BNS
BNS is the main national multipurpose sports stadium in Dhaka, Bangladesh, historically used for major football and cricket events.
 E580546 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: BNS | Statement: [Bangabandhu National Stadium, alsoKnownAs, BNS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BNS
Context triple: [Bangabandhu National Stadium, alsoKnownAs, BNS]
  • A. BNS
    BNS is the stock ticker symbol for the Bank of Nova Scotia, one of Canada’s largest multinational banks.
  • B. BNS (NYSE)
    BNS (NYSE) is the stock ticker symbol for The Bank of Nova Scotia, one of Canada's largest multinational banks.
  • C. BND
    BND is the official currency code for the Brunei dollar, the national currency of Brunei Darussalam.
  • D. BND
    BND is the three-letter station code used to identify Bond Street station on the London Underground network.
  • E. BRN
    BRN is the IATA airport code for Bern Airport, the primary airport serving Switzerland’s capital city.
  • 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: BNS
Triple: [Bangabandhu National Stadium, alsoKnownAs, BNS]
Generated description
BNS is the main national multipurpose sports stadium in Dhaka, Bangladesh, historically used for major football and cricket events.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BNS
Target entity description: BNS is the main national multipurpose sports stadium in Dhaka, Bangladesh, historically used for major football and cricket events.
  • A. BNS
    BNS is the stock ticker symbol for the Bank of Nova Scotia, one of Canada’s largest multinational banks.
  • B. BNS (NYSE)
    BNS (NYSE) is the stock ticker symbol for The Bank of Nova Scotia, one of Canada's largest multinational banks.
  • C. BND
    BND is the official currency code for the Brunei dollar, the national currency of Brunei Darussalam.
  • D. BND
    BND is the three-letter station code used to identify Bond Street station on the London Underground network.
  • E. BRN
    BRN is the IATA airport code for Bern Airport, the primary airport serving Switzerland’s capital city.
  • 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_69c008b4858c819095b0199114a9a87b completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0633dde348190bbf02a943d94e3be completed March 22, 2026, 9:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c2441d4ad88190895237d834f5d9b8 completed March 24, 2026, 7:58 a.m.
NEDg Description generation batch_69c2a571b6708190a93f750852365525 completed March 24, 2026, 2:53 p.m.
NED2 Entity disambiguation (via description) batch_69c4fb839b2481909caa57f34a8837db completed March 26, 2026, 9:25 a.m.
Created at: March 22, 2026, 4:24 p.m.