Triple

T4098471
Position Surface form Disambiguated ID Type / Status
Subject Helsinki Airport E87879 entity
Predicate hasTerminal P182 FINISHED
Object Terminal 1
Terminal 1 is one of the main passenger terminals at Helsinki Airport, serving as a hub for various international and domestic flights.
E415400 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 1 | Statement: [Helsinki Airport, hasTerminal, Terminal 1]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 1
Context triple: [Helsinki Airport, hasTerminal, Terminal 1]
  • A. Terminal 1
    Terminal 1 is one of the passenger terminals at Los Angeles International Airport, primarily serving domestic flights for several major U.S. airlines.
  • B. Terminal 1
    Terminal 1 is a passenger terminal at San Francisco International Airport that serves as one of the airport’s main facilities for airline check-in, security, and boarding.
  • C. Terminal 1
    Terminal 1 is one of the main passenger terminals at San Diego International Airport, serving various domestic airline operations and traveler amenities.
  • D. Terminal 1
    Terminal 1 is one of the passenger terminals at Raleigh–Durham International Airport, serving as a primary facility for airline check-in, security screening, and boarding.
  • E. Terminal 1
    Terminal 1 is the main passenger terminal at Geneva Airport, handling the majority of the airport’s commercial flights and services.
  • 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 1
Triple: [Helsinki Airport, hasTerminal, Terminal 1]
Generated description
Terminal 1 is one of the main passenger terminals at Helsinki Airport, serving as a hub for various international and domestic flights.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terminal 1
Target entity description: Terminal 1 is one of the main passenger terminals at Helsinki Airport, serving as a hub for various international and domestic flights.
  • A. Terminal 1
    Terminal 1 is one of the main passenger terminals at Hamburg Airport, serving as a hub for check-in, security, and boarding operations.
  • B. Terminal 1
    Terminal 1 is a major passenger terminal at Toronto Pearson International Airport, serving as one of the airport’s primary hubs for domestic and international flights.
  • C. Terminal 1
    Terminal 1 is one of the main passenger terminals at Zurich Airport, handling check-in, security, and boarding for a variety of international and domestic flights.
  • D. Terminal 1
    Terminal 1 is one of the main passenger terminals at Cairo International Airport, serving various international and domestic flights.
  • E. Terminal 1
    Terminal 1 is one of the main passenger terminals at Vienna International Airport, serving various airlines with check-in, security, and boarding facilities.
  • 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_69aed94564cc8190a9c1457daedb6e7f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefce017708190a4d33753fd32a7bb completed March 9, 2026, 5:01 p.m.
NED1 Entity disambiguation (via context triple) batch_69b576a1a0408190aa4683a0904790aa completed March 14, 2026, 2:54 p.m.
NEDg Description generation batch_69b576fb7fa08190ada0dff7aa581665 completed March 14, 2026, 2:55 p.m.
NED2 Entity disambiguation (via description) batch_69b5778dcdc08190aee087f6d54992dc completed March 14, 2026, 2:58 p.m.
Created at: March 9, 2026, 3:40 p.m.