Triple
T18796976
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saab 9-X concept |
E459659
|
entity |
| Predicate | designer |
P184
|
FINISHED |
| Object | Michael Mauer |
—
|
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: Michael Mauer | Statement: [Saab 9-X concept, designer, Michael Mauer]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Mauer Context triple: [Saab 9-X concept, designer, Michael Mauer]
-
A.
Michael Mauer
chosen
Michael Mauer is a German automobile designer best known as Porsche’s longtime head of design, responsible for shaping models such as the Panamera, 911, and Cayenne.
-
B.
Glen Bateman
Glen Bateman is a retired sociology professor and key survivor character in Stephen King's post-apocalyptic novel "The Stand," known for his analytical perspective on the collapse and rebuilding of society.
-
C.
Kevin Sussman
Kevin Sussman is an American actor and comedian best known for his role as Stuart Bloom on the television series "The Big Bang Theory."
-
D.
Jay Karas
Jay Karas is an American film and television director known for his work on stand-up comedy specials and various TV series.
-
E.
Allan Havey
Allan Havey is an American stand-up comedian and actor known for his sharp observational humor and numerous television and film roles.
- 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_69d8d398c7d4819091cb2f7e48948aeb |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5a020821881909749f6a1c6cd195b |
completed | April 20, 2026, 3:40 a.m. |
Created at: April 10, 2026, 11:53 a.m.