Triple

T20891370
Position Surface form Disambiguated ID Type / Status
Subject Grob G 520 Egrett E514414 entity
Predicate manufacturer P490 FINISHED
Object Grob Aerospace 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 Aerospace | Statement: [Grob G 520 Egrett, manufacturer, Grob Aerospace]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Grob Aerospace
Context triple: [Grob G 520 Egrett, manufacturer, Grob Aerospace]
  • A. Grob Aircraft chosen
    Grob Aircraft is a German aerospace manufacturer known for producing composite training and aerobatic aircraft for civil and military use.
  • B. Berliner Aircraft Company
    Berliner Aircraft Company was an early 20th-century American aviation firm known for its experimental work in helicopter and vertical flight development.
  • C. Bücker Flugzeugbau
    Bücker Flugzeugbau was a German aircraft manufacturer best known for producing light training and sport biplanes in the 1930s and 1940s.
  • D. Ferris Aircraft
    Ferris Aircraft is a fictional aerospace company in DC Comics best known as the workplace of test pilot Hal Jordan, who becomes the superhero Green Lantern.
  • E. Pilatus Aircraft
    Pilatus Aircraft is a Swiss aerospace manufacturer best known for producing high-performance turboprop training and utility aircraft for military and civilian use.
  • 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_69e0b4f7ebe48190952a85547a0f31a1 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6d05e307081908f1d044e877017ec completed April 21, 2026, 1:18 a.m.
Created at: April 16, 2026, 12:46 p.m.