Triple

T20457932
Position Surface form Disambiguated ID Type / Status
Subject Hedwig Eva Maria Kiesler E501844 entity
Predicate spouse P13 FINISHED
Object Teddy Stauffer 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: Teddy Stauffer | Statement: [Hedwig Eva Maria Kiesler, spouse, Teddy Stauffer]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Teddy Stauffer
Context triple: [Hedwig Eva Maria Kiesler, spouse, Teddy Stauffer]
  • A. Teddy Stauffer chosen
    Teddy Stauffer was a Swiss-born bandleader and musician, prominent in the swing era and later active in the entertainment and hospitality industries.
  • B. Johnny Stachela
    Johnny Stachela is an American guitarist best known for his work with The Allman Betts Band, where he contributes to their modern Southern rock sound.
  • C. Max Stottlemeyer
    Max Stottlemeyer is the son of San Francisco Police Captain Leland Stottlemeyer from the television series "Monk."
  • D. Charlie Staadecker
    Charlie Staadecker is a Seattle businessman and civic leader who ran as a candidate in the 2013 Seattle mayoral election.
  • E. Don Ettlinger
    Don Ettlinger was a screenwriter active in early 20th-century American cinema, known for adapting popular literary works for the screen.
  • 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_69e0b4ad4940819098cf2ff6413574e5 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e696a2a8a88190992211b09295d8ea completed April 20, 2026, 9:12 p.m.
Created at: April 16, 2026, 11:33 a.m.