Triple

T7357492
Position Surface form Disambiguated ID Type / Status
Subject Doncaster Sheffield Airport E169661 entity
Predicate IATAcode P418 FINISHED
Object DSA
DSA is the three-letter IATA airport code for Doncaster Sheffield Airport in South Yorkshire, England.
 E658818 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: DSA | Statement: [Doncaster Sheffield Airport, IATAcode, DSA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DSA
Context triple: [Doncaster Sheffield Airport, IATAcode, DSA]
  • A. DSA
    DSA is India’s tri-service Defence Space Agency responsible for coordinating and enhancing the country’s military space capabilities.
  • B. DSA
    DSA (Digital Signature Algorithm) is a widely used public-key cryptographic standard designed for creating and verifying digital signatures to ensure data integrity and authentication.
  • C. DAA
    DAA is the IATA airport code for Davison Army Airfield, a U.S. Army aviation facility located at Fort Belvoir, Virginia.
  • D. DS
    DS is the standardized Diploma Supplement used across the European Higher Education Area to provide transparent, comparable information about higher education qualifications.
  • E. DS
    DS was the communist-era Bulgarian State Security service, responsible for internal repression, intelligence, and secret police activities in the People’s Republic of Bulgaria.
  • 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: DSA
Triple: [Doncaster Sheffield Airport, IATAcode, DSA]
Generated description
DSA is the three-letter IATA airport code for Doncaster Sheffield Airport in South Yorkshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DSA
Target entity description: DSA is the three-letter IATA airport code for Doncaster Sheffield Airport in South Yorkshire, England.
  • A. DSA
    DSA (Digital Signature Algorithm) is a widely used public-key cryptographic standard designed for creating and verifying digital signatures to ensure data integrity and authentication.
  • B. DSA
    DSA is India’s tri-service Defence Space Agency responsible for coordinating and enhancing the country’s military space capabilities.
  • C. DAA
    DAA is the IATA airport code for Davison Army Airfield, a U.S. Army aviation facility located at Fort Belvoir, Virginia.
  • D. DS
    DS is the standardized Diploma Supplement used across the European Higher Education Area to provide transparent, comparable information about higher education qualifications.
  • E. DS
    DS was the communist-era Bulgarian State Security service, responsible for internal repression, intelligence, and secret police activities in the People’s Republic of Bulgaria.
  • 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_69c68a59f2288190877ca15c19b1e822 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f13bf2e881909bc95b93a5664a4f completed March 27, 2026, 9:06 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7faaa8ec8819093bf6b4562472288 completed March 28, 2026, 3:58 p.m.
NEDg Description generation batch_69c7fc5d7e5081908c9f7389f4dea1e0 completed March 28, 2026, 4:05 p.m.
NED2 Entity disambiguation (via description) batch_69c7fcb5f7f0819081e70f8809bb34ae completed March 28, 2026, 4:07 p.m.
Created at: March 27, 2026, 3:06 p.m.