Triple

T17324371
Position Surface form Disambiguated ID Type / Status
Subject GMMN E420647 entity
Predicate hasPassengerTerminal P1297 FINISHED
Object Terminal 2 NE ONDG

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 2 | Statement: [GMMN, hasPassengerTerminal, Terminal 2]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 2
Context triple: [GMMN, hasPassengerTerminal, Terminal 2]
  • A. Terminal 2
    Terminal 2 is a modern, sustainably designed passenger terminal at San Francisco International Airport known for its upgraded amenities, art installations, and improved traveler experience.
  • B. Terminal 2
    Terminal 2 is the modern international passenger terminal at Nội Bài International Airport in Hanoi, Vietnam, serving most of the airport’s international flights.
  • C. Terminal 2
    Terminal 2 is the main, modern passenger terminal at Shanghai Hongqiao International Airport, handling the majority of the airport’s domestic and some international flights.
  • D. Terminal 2
    Terminal 2 is a secondary passenger terminal at Kota Kinabalu International Airport in Sabah, Malaysia, serving regional and low-cost airline operations.
  • E. Terminal 2
    Terminal 2 is one of the passenger terminals serving Iași International Airport in Romania, handling check-in, departures, and arrivals for commercial 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 2
Triple: [GMMN, hasPassengerTerminal, Terminal 2]
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terminal 2
Target entity description: Terminal 2 is a passenger terminal at Mohammed V International Airport (GMMN) in Casablanca, Morocco, serving commercial air travelers and airline operations.
  • A. Terminal 2
    Terminal 2 is one of the main passenger terminals at Marrakesh Menara Airport, serving travelers to and from the Moroccan city of Marrakesh.
  • B. Terminal 2
    Terminal 2 is one of the main passenger terminals at Málaga Airport in Spain, handling a significant share of the airport’s domestic and international flights.
  • C. Terminal 2
    Terminal 2 is one of the main passenger terminals at Cairo International Airport, serving a mix of international and regional flights.
  • D. Terminal 2
    Terminal 2 is a passenger terminal at Sharm El Sheikh International Airport in Egypt, serving as one of the airport’s main facilities for handling domestic and international flights.
  • E. Terminal 2
    Terminal 2 is one of the main passenger terminals at King Khalid International Airport in Riyadh, Saudi Arabia, serving regional and international flights.
  • F. None of above. chosen

Provenance (4 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_69d889d3adc881909319f1edb8d2a956 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e439d18e3081908ca15baa743abcd8 completed April 19, 2026, 2:11 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01954ecadc8190a6484ff0a207fe9b completed May 11, 2026, 8:37 a.m.
NEDg Description generation batch_6a01964923248190b0c3548d90bc1dd9 in_progress May 11, 2026, 8:41 a.m.
Created at: April 10, 2026, 5:43 a.m.