Triple
T26376136
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christian Sauter |
E660904
|
entity |
| Predicate | electoral office |
P1239
|
FINISHED |
| Object | Member of the Bundestag |
—
|
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: Member of the Bundestag | Statement: [Christian Sauter, electoral office, Member of the Bundestag]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electoral office Context triple: [Christian Sauter, electoral office, Member of the Bundestag]
-
A.
electedOffice
chosen
Indicates that an entity holds or has held a particular office or position as a result of an election.
-
B.
electionForOffice
Indicates that an election event is held to select or fill a specific office or position.
-
C.
electoralPosition
Indicates that an entity holds, has held, or is a candidate for a specific role or office within an electoral or political system.
-
D.
isElectoralOffice
Indicates that the referenced position or role is an official public office filled through an electoral process.
-
E.
electoralRole
Indicates the specific function, position, or capacity an entity holds within an electoral process or system.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 26, 2026, 11:01 p.m.