Triple

T18323095
Position Surface form Disambiguated ID Type / Status
Subject Airside Terminal E438932 entity
Predicate hasPart P35 FINISHED
Object Concourse D NE NERFINISHED

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: Concourse D | Statement: [Airside Terminal, hasPart, Concourse D]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Concourse D
Context triple: [Airside Terminal, hasPart, Concourse D]
  • A. Concourse D chosen
    Concourse D is one of the passenger terminal concourses at Hartsfield–Jackson Atlanta International Airport, serving numerous domestic flights and airline gates.
  • B. Concourse D
    Concourse D is a former passenger terminal concourse at Cleveland Hopkins International Airport that primarily served as a hub for regional jet operations.
  • C. Concourse D
    Concourse D is a passenger terminal area at Southwest Florida International Airport serving airline gates and related airport services.
  • D. Concourse D
    Concourse D is a passenger terminal area at Harry Reid International Airport in Las Vegas that serves multiple airline gates and flight operations.
  • E. Concourse D
    Concourse D is a passenger terminal area at Nashville International Airport that serves airline gates, boarding, and related airport services.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d8b916a2d081909e249e4902f6aad9 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e50aa886508190902ffc26b30731ae completed April 19, 2026, 5:02 p.m.
Created at: April 10, 2026, 10:36 a.m.