Triple

T8095743
Position Surface form Disambiguated ID Type / Status
Subject Aspern E188979 entity
Predicate hasLandmark P105 FINISHED
Object Aspern Airfield E709044 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: Aspern Airfield | Statement: [Aspern, hasLandmark, Aspern Airfield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Aspern Airfield
Context triple: [Aspern, hasLandmark, Aspern Airfield]
  • A. Aspern Airfield chosen
    Aspern Airfield was a historic airfield in Vienna, Austria, that served as one of the country’s earliest and most important aviation hubs before its closure and redevelopment.
  • B. Egelsbach Airfield
    Egelsbach Airfield is a general aviation airport in Hesse, Germany, serving as a busy hub for business and private flights near Frankfurt.
  • C. Preschen Air Base
    Preschen Air Base was a major Cold War-era military airfield in East Germany that served as an important operational base for the East German Air Force.
  • D. Neuburg Air Base
    Neuburg Air Base is a major Luftwaffe installation in Bavaria that serves as one of Germany’s key fighter aircraft bases.
  • E. Annemasse Aerodrome
    Annemasse Aerodrome is a small regional airport in southeastern France serving general aviation and access to the Annemasse–Geneva area.
  • 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_69ca82b886d88190a9cba0d5a4a27521 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb4291f1d4819098985ac2b20b6c75 completed March 31, 2026, 3:42 a.m.
NED1 Entity disambiguation (via context triple) batch_69cc93ff6a108190ac60218ec2716c60 completed April 1, 2026, 3:41 a.m.
Created at: March 30, 2026, 5:30 p.m.