Triple

T6862416
Position Surface form Disambiguated ID Type / Status
Subject MEL E158312 entity
Predicate hasTerminal P182 FINISHED
Object Terminal 4
Terminal 4 is a passenger terminal at Melbourne Airport (MEL) primarily serving low-cost and domestic airlines.
E175011 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 4 | Statement: [MEL, hasTerminal, Terminal 4]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 4
Context triple: [MEL, hasTerminal, Terminal 4]
  • A. Terminal 4
    Terminal 4 is one of Heathrow Airport’s passenger terminals, serving a mix of international airlines and routes with its own check-in, security, and arrivals facilities.
  • B. Terminal 4
    Terminal 4 is one of the passenger terminals at Stockholm Arlanda Airport, primarily serving domestic and some regional flights within Scandinavia.
  • C. Terminal 4
    Terminal 4 is a passenger terminal facility at King Khalid International Airport in Riyadh, Saudi Arabia, serving commercial air traffic with check-in, boarding, and arrival services.
  • D. Terminal 4
    Terminal 4 is one of the passenger terminals at Perth Airport in Western Australia, serving selected domestic airline operations.
  • E. Terminal 4
    Terminal 4 is a major passenger terminal at Cancún International Airport that handles a large share of the airport’s international and domestic 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 4
Triple: [MEL, hasTerminal, Terminal 4]
Generated description
Terminal 4 is a passenger terminal at Melbourne Airport (MEL) primarily serving low-cost and domestic airlines.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terminal 4
Target entity description: Terminal 4 is a passenger terminal at Melbourne Airport (MEL) primarily serving low-cost and domestic airlines.
  • A. Terminal 4 chosen
    Terminal 4 is a budget-focused domestic terminal at Melbourne Airport that primarily serves low-cost and regional airlines.
  • B. Terminal 4
    Terminal 4 is one of the passenger terminals at Perth Airport in Western Australia, serving selected domestic airline operations.
  • C. Terminal 4
    Terminal 4 is one of Heathrow Airport’s passenger terminals, serving a mix of international airlines and routes with its own check-in, security, and arrivals facilities.
  • D. Terminal 4
    Terminal 4 is one of the main passenger terminals at Ontario International Airport in Southern California, serving domestic airline operations and traveler amenities.
  • E. Terminal 4
    Terminal 4 is one of the passenger terminals at Ninoy Aquino International Airport in Manila, primarily serving domestic flights with basic, low-cost carrier facilities.
  • 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_69c68830cdbc8190a8301c7a9d9f651a completed March 27, 2026, 1:37 p.m.
NER Named-entity recognition batch_69c6d887d6648190a0c2d1cb1b284bfe completed March 27, 2026, 7:20 p.m.
NED1 Entity disambiguation (via context triple) batch_69c72fed3e788190b2b68fc93173f73e completed March 28, 2026, 1:33 a.m.
NEDg Description generation batch_69c7361177ac8190b1e06cb15d258d0f completed March 28, 2026, 1:59 a.m.
NED2 Entity disambiguation (via description) batch_69c7381015a081909f9b32732f826d2c completed March 28, 2026, 2:08 a.m.
Created at: March 27, 2026, 2:21 p.m.