Triple

T20886807
Position Surface form Disambiguated ID Type / Status
Subject Mattsies E514302 entity
Predicate hasFacility P105 FINISHED
Object Grob Aircraft airfield 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: Grob Aircraft airfield | Statement: [Mattsies, hasFacility, Grob Aircraft airfield]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grob Aircraft airfield
Context triple: [Mattsies, hasFacility, Grob Aircraft airfield]
  • A. Grob Aircraft airfield chosen
    Grob Aircraft airfield is a private airfield in Mattsies, Germany, primarily used for the testing, production, and operation of Grob Aircraft’s light aircraft.
  • B. Grenseland airfield
    Grenseland airfield was a former airfield serving the Kirkenes area in Norway before being superseded by the larger Kirkenes Airport, Høybuktmoen.
  • C. Balli-Doogle Airfield
    Balli-Doogle Airfield is a military airfield in Somalia that has served as a key operational base for Somali and international forces.
  • D. Mestersvig airfield
    Mestersvig airfield is a small remote airstrip in eastern Greenland that serves the former mining settlement and nearby scientific and military installations in the Mestersvig area.
  • E. Juist Airfield
    Juist Airfield is a small regional airport serving the North Sea island of Juist in Germany, providing vital air connections for residents and tourists.
  • 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_69e0b4f733f081908a401c0b7beb0b9f completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d058d4dc81908398f8c75e30dc77 completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.