Triple

T3891256
Position Surface form Disambiguated ID Type / Status
Subject Terminal 5 E88066 entity
Predicate hasSubTerminal P15145 FINISHED
Object Terminal 5A
Terminal 5A is a sub-section of Heathrow Airport’s Terminal 5, primarily serving British Airways flights with dedicated gates and passenger facilities.
 E88066 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: Terminal 5A | Statement: [Terminal 5, hasSubTerminal, Terminal 5A]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Terminal 5A
Context triple: [Terminal 5, hasSubTerminal, Terminal 5A]
  • A. Terminal 5
    Terminal 5 is a passenger terminal facility at Kuwait International Airport serving commercial air travelers.
  • B. Terminal 5
    Terminal 5 is a major, modern passenger terminal at London Heathrow Airport primarily serving British Airways and Iberia flights.
  • C. Terminal 5
    Terminal 5 is one of the passenger terminals at Los Angeles International Airport, serving a mix of domestic and some international flights with various airlines and amenities.
  • D. Terminal 5
    Terminal 5 is a dedicated passenger terminal at Rome’s Leonardo da Vinci–Fiumicino Airport, primarily used for certain international and long-haul flights.
  • E. Terminal 5
    Terminal 5 is a passenger terminal facility at Mehrabad International Airport in Tehran, Iran.
  • 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: Terminal 5A
Triple: [Terminal 5, hasSubTerminal, Terminal 5A]
Generated description
Terminal 5A is a sub-section of Heathrow Airport’s Terminal 5, primarily serving British Airways flights with dedicated gates and passenger facilities.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Terminal 5A
Target entity description: Terminal 5A is a sub-section of Heathrow Airport’s Terminal 5, primarily serving British Airways flights with dedicated gates and passenger facilities.
  • A. Terminal 5 chosen
    Terminal 5 is a major, modern passenger terminal at London Heathrow Airport primarily serving British Airways and Iberia flights.
  • B. Terminal 5
    Terminal 5 is a passenger terminal facility at Kuwait International Airport serving commercial air travelers.
  • C. Terminal 5
    Terminal 5 is one of the passenger terminals at José Martí International Airport in Havana, Cuba, serving specific airlines and routes.
  • D. Terminal 5
    Terminal 5 is one of the passenger terminals at Los Angeles International Airport, serving a mix of domestic and some international flights with various airlines and amenities.
  • E. Terminal 5
    Terminal 5 is a dedicated passenger terminal at Rome’s Leonardo da Vinci–Fiumicino Airport, primarily used for certain international and long-haul flights.
  • F. None of above.

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_69aed9466d548190939f5217a23ed4ac completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeecb0ba448190aa076865b7762002 completed March 9, 2026, 3:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69b51c91d41c8190868ce530d58b5516 completed March 14, 2026, 8:30 a.m.
NEDg Description generation batch_69b51d21f9148190914639d9048f9f8e completed March 14, 2026, 8:32 a.m.
NED2 Entity disambiguation (via description) batch_69b51dd884bc8190bf660c4eb70eccb1 completed March 14, 2026, 8:35 a.m.
Created at: March 9, 2026, 3:21 p.m.