Triple

T13156406
Position Surface form Disambiguated ID Type / Status
Subject Dornier Do 335 Pfeil E312599 entity
Predicate ejectionSystem P94293 FINISHED
Object ejection seat LITERAL 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: ejection seat | Statement: [Dornier Do 335 Pfeil, ejectionSystem, ejection seat]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: ejectionSystem
Context triple: [Dornier Do 335 Pfeil, ejectionSystem, ejection seat]
  • A. hasEjectionSeat chosen
    Indicates that an object (typically a vehicle or cockpit) is equipped with an ejection seat that allows an occupant to be forcibly expelled for emergency escape.
  • B. parachuteSystem
    Indicates that one entity functions as a parachute system used to safely decelerate or recover another entity.
  • C. hasLiftOrLaunchSystem
    Indicates that an entity is equipped with, or associated with, a system used to lift, launch, or otherwise deploy another object or vehicle.
  • D. hasVerticalLaunchSystem
    Indicates that one entity is equipped with a vertical launch system used to fire missiles or similar munitions vertically.
  • E. hasEjecta
    Indicates that one entity produces or is associated with material expelled or thrown out from another entity as a result of an energetic event or process.
  • F. None of above.

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_69d806aabde48190899e13e41659cae5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98cf054f88190b05ced98d5a22a62 completed April 10, 2026, 11:51 p.m.
PD Predicate disambiguation batch_69d98bbd1d088190b7c69f37fc6eeb64 completed April 10, 2026, 11:46 p.m.
Created at: April 9, 2026, 9:12 p.m.