Triple

T20643220
Position Surface form Disambiguated ID Type / Status
Subject Terminal A (Hannover Airport) E507282 entity
Predicate connectedTo P37 FINISHED
Object Terminal B (Hannover Airport) NE NERFINISHED

How this triple was built (3 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 B (Hannover Airport) | Statement: [Terminal A (Hannover Airport), connectedTo, Terminal B (Hannover Airport)]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal B (Hannover Airport)
Context triple: [Terminal A (Hannover Airport), connectedTo, Terminal B (Hannover Airport)]
  • A. Terminal 1 (Hamburg Airport)
    Terminal 1 at Hamburg Airport is a modern passenger terminal handling check-in, security, and boarding operations for various airlines at the international airport serving Hamburg, Germany.
  • B. Terminal 1 (Frankfurt Airport)
    Terminal 1 at Frankfurt Airport is the airport’s largest and oldest terminal, serving as a major hub for Lufthansa and Star Alliance carriers with extensive international and domestic flight operations.
  • C. Hannover Airport
    Hannover Airport is an international airport serving the city of Hanover in northern Germany, handling passenger and cargo flights for the region.
  • D. Terminal 2 of Berlin Brandenburg Airport
    Terminal 2 of Berlin Brandenburg Airport is a passenger terminal facility designed to handle additional low-cost and leisure airline traffic alongside the airport’s main Terminal 1 complex.
  • E. Terminal 1 of Berlin Brandenburg Airport
    Terminal 1 of Berlin Brandenburg Airport is the airport’s main passenger terminal, housing the primary check-in, security, and boarding facilities for most airlines and flights.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Terminal B (Hannover Airport)
Target entity description: Terminal B at Hannover Airport is one of the airport’s main passenger terminals, handling check-in, security, and boarding for a portion of its domestic and international flights.
  • A. Terminal 1 (Hamburg Airport)
    Terminal 1 at Hamburg Airport is a modern passenger terminal handling check-in, security, and boarding operations for various airlines at the international airport serving Hamburg, Germany.
  • B. Terminal 1 (Frankfurt Airport)
    Terminal 1 at Frankfurt Airport is the airport’s largest and oldest terminal, serving as a major hub for Lufthansa and Star Alliance carriers with extensive international and domestic flight operations.
  • C. Hannover Airport chosen
    Hannover Airport is an international airport serving the city of Hanover in northern Germany, handling passenger and cargo flights for the region.
  • D. Terminal 2 of Berlin Brandenburg Airport
    Terminal 2 of Berlin Brandenburg Airport is a passenger terminal facility designed to handle additional low-cost and leisure airline traffic alongside the airport’s main Terminal 1 complex.
  • E. Terminal 1 of Berlin Brandenburg Airport
    Terminal 1 of Berlin Brandenburg Airport is the airport’s main passenger terminal, housing the primary check-in, security, and boarding facilities for most airlines and flights.
  • F. None of above.

Provenance (2 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_69e0b4be702c8190a3d2410a881d310a completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6af1c51f48190abba54a5aace9fc8 completed April 20, 2026, 10:56 p.m.
Created at: April 16, 2026, 11:43 a.m.