Triple

T3006497
Position Surface form Disambiguated ID Type / Status
Subject Saab 32 Lansen E81913 entity
Predicate successor P78 FINISHED
Object Saab 37 Viggen E81705 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: Saab 37 Viggen | Statement: [Saab 32 Lansen, successor, Saab 37 Viggen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saab 37 Viggen
Context triple: [Saab 32 Lansen, successor, Saab 37 Viggen]
  • A. Saab 37 Viggen chosen
    The Saab 37 Viggen is a Swedish multirole combat aircraft introduced in the 1970s, known for its distinctive canard-delta design and short takeoff and landing capability for dispersed road-base operations.
  • B. Saab 35 Draken
    The Saab 35 Draken is a Swedish Cold War-era supersonic fighter aircraft known for its distinctive double-delta wing design and service with several European air forces.
  • C. Saab 32 Lansen
    The Saab 32 Lansen is a Swedish Cold War-era jet aircraft designed as a multi-role attack and reconnaissance platform for the Swedish Air Force.
  • D. Saab 340
    The Saab 340 is a twin‑engine turboprop regional airliner widely used for short-haul passenger services around the world.
  • E. Saab 2000
    The Saab 2000 is a high-speed twin‑engine turboprop regional airliner developed in the 1990s, known for its fast cruise performance and efficient short- to medium-haul operations.
  • 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_69ad8b1c4de88190a83b7cefaa1f2842 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a48f0888190bdec150dac623851 completed March 8, 2026, 3:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69b1dea3a31481908db6871cf6c37781 completed March 11, 2026, 9:29 p.m.
Created at: March 8, 2026, 3 p.m.