Triple

T2594702
Position Surface form Disambiguated ID Type / Status
Subject Dornier Do 217 E58200 entity
Predicate predecessor P97 FINISHED
Object Dornier Do 215 E338473 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: Dornier Do 215 | Statement: [Dornier Do 217, predecessor, Dornier Do 215]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Dornier Do 215
Context triple: [Dornier Do 217, predecessor, Dornier Do 215]
  • A. Dornier Do 215 chosen
    The Dornier Do 215 was a German World War II twin-engine bomber and reconnaissance aircraft derived from the earlier Do 17 design.
  • B. Dornier Do 31
    The Dornier Do 31 was a German experimental vertical take-off and landing (VTOL) jet transport aircraft developed in the 1960s for potential military airlift use.
  • C. Dornier Do 24
    The Dornier Do 24 is a German World War II-era three-engine flying boat primarily used for maritime patrol, search and rescue, and reconnaissance missions.
  • D. Dornier Do X
    The Dornier Do X was a massive German flying boat of the late 1920s and early 1930s, famous for being one of the largest and most ambitious passenger aircraft of its time.
  • E. Dornier Do 28
    The Dornier Do 28 is a German twin-engine STOL utility aircraft developed in the 1960s for short takeoff and landing operations on rough or unprepared airstrips.
  • 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_69ab4ac14040819098b13f4a27d5c8ff completed March 6, 2026, 9:44 p.m.
NER Named-entity recognition batch_69abd427f58c8190af1c1a9724158c96 completed March 7, 2026, 7:30 a.m.
NED1 Entity disambiguation (via context triple) batch_69b367dc88ac81909e73e290c745b8be completed March 13, 2026, 1:26 a.m.
Created at: March 6, 2026, 9:49 p.m.