Triple

T4375982
Position Surface form Disambiguated ID Type / Status
Subject Terminal 2G E99006 entity
Predicate partOf P40 FINISHED
Object Terminal 2 complex E342707 NE FINISHED

How this triple was built (2 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 complex | Statement: [Terminal 2G, partOf, Terminal 2 complex]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Terminal 2 complex
Context triple: [Terminal 2G, partOf, Terminal 2 complex]
  • A. Terminal 2 complex chosen
    Terminal 2 complex is a major multi-terminal passenger facility at Paris Charles de Gaulle Airport that groups several interconnected sub-terminals and services.
  • B. Terminal 3
    Terminal 3 is one of the main passenger terminals at Leonardo da Vinci–Fiumicino Airport in Rome, handling a large share of the airport’s international and domestic flights.
  • C. Terminal 3
    Terminal 3 is a passenger terminal at Cincinnati/Northern Kentucky International Airport serving airline operations and traveler services.
  • D. Terminal 3
    Terminal 3 is Haneda Airport’s international terminal in Tokyo, serving as a major hub for overseas flights and passenger services.
  • E. Terminal 3
    Terminal 3 is one of the passenger terminals at Mehrabad International Airport in Tehran, serving domestic air traffic within Iran.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69b3454ea8f48190a49c2436624d6ef6 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b3523d4e888190b4367ed6aa17d463 completed March 12, 2026, 11:54 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5e5162d5081909e7d8813907e25a6 completed March 14, 2026, 10:45 p.m.
Created at: March 12, 2026, 11:18 p.m.