Triple

T4688862
Position Surface form Disambiguated ID Type / Status
Subject Arlanda Central Station E103984 entity
Predicate servesTerminal P20599 FINISHED
Object Terminal 5
Terminal 5 is the largest and main international passenger terminal at Stockholm Arlanda Airport in Sweden.
E125268 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 5 | Statement: [Arlanda Central Station, servesTerminal, Terminal 5]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 5
Context triple: [Arlanda Central Station, servesTerminal, Terminal 5]
  • A. Terminal 5
    Terminal 5 is one of the passenger terminals at José Martí International Airport in Havana, Cuba, serving specific airlines and routes.
  • 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 the international terminal at Chicago O'Hare International Airport, serving most of the airport’s non-domestic and many foreign-flag carriers.
  • D. Terminal 5
    Terminal 5 is a major passenger terminal at John F. Kennedy International Airport in New York City, known for serving as the primary hub for JetBlue Airways.
  • 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. 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 5
Triple: [Arlanda Central Station, servesTerminal, Terminal 5]
Generated description
Terminal 5 is the largest and main international passenger terminal at Stockholm Arlanda Airport in Sweden.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terminal 5
Target entity description: Terminal 5 is the largest and main international passenger terminal at Stockholm Arlanda Airport in Sweden.
  • A. Terminal 5 chosen
    Terminal 5 is the main international passenger terminal at Stockholm Arlanda Airport, handling a large share of the airport’s long-haul and major European flights.
  • B. 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.
  • C. Terminal 5
    Terminal 5 is a major, modern passenger terminal at London Heathrow Airport primarily serving British Airways and Iberia flights.
  • D. Terminal 5
    Terminal 5 is a passenger terminal facility at Mehrabad International Airport in Tehran, Iran.
  • E. Terminal 5
    Terminal 5 is the international terminal at Chicago O'Hare International Airport, serving most of the airport’s non-domestic and many foreign-flag carriers.
  • 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_69bd43df91f481908e9add1b617b60ef completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd6399621881909aa8ffb1c27284e9 completed March 20, 2026, 3:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69be67bb17e0819099a6d4f3ca54f616 completed March 21, 2026, 9:41 a.m.
NEDg Description generation batch_69be6bd61d7c819083c7d8cf9cb774d2 completed March 21, 2026, 9:58 a.m.
NED2 Entity disambiguation (via description) batch_69be6c2f99788190a8e80bb95fe08726 completed March 21, 2026, 10 a.m.
Created at: March 20, 2026, 1:16 p.m.