Triple
T20272440
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMW Headquarters |
E502923
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Karl Schwanzer |
—
|
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: Karl Schwanzer | Statement: [BMW Headquarters, architect, Karl Schwanzer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karl Schwanzer Context triple: [BMW Headquarters, architect, Karl Schwanzer]
-
A.
Karl Schwanzer
chosen
Karl Schwanzer was an Austrian modernist architect renowned for innovative designs such as Munich’s iconic BMW headquarters and museum complex.
-
B.
Karl Kling
Karl Kling was a German racing driver of the 1950s who competed for the Mercedes-Benz works team in Grand Prix and sports car events.
-
C.
Carl Schwachheim
Carl Schwachheim was an archaeologist known for discovering the Lindenmeier site, a major Folsom culture Paleo-Indian campsite in Colorado.
-
D.
Karl Pfirsch
Karl Pfirsch was a German industrialist who stood as a defendant in the Nuremberg Military Tribunal’s Case X for his involvement in Nazi-era economic activities.
-
E.
Karl Blank
Karl Blank was an 18th-century Russian architect known for his significant contributions to neoclassical architecture in Moscow.
- 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_69e0b4b0e79c8190bd61f22ef1329fa8 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e675dff3c4819098ba45eba4e7b296 |
completed | April 20, 2026, 6:52 p.m. |
Created at: April 16, 2026, 10:15 a.m.