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.