Triple
T18896650
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Timo Salonen |
E462225
|
entity |
| Predicate | carDriven |
P7364
|
FINISHED |
| Object | Mazda 323 4WD |
—
|
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: Mazda 323 4WD | Statement: [Timo Salonen, carDriven, Mazda 323 4WD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mazda 323 4WD Context triple: [Timo Salonen, carDriven, Mazda 323 4WD]
-
A.
Mazda 323
chosen
The Mazda 323 is a compact car produced by Mazda that gained popularity worldwide for its practicality, reliability, and efficient performance across multiple generations.
-
B.
Mazda B-Series
The Mazda B-Series is a line of compact pickup trucks produced by Mazda over several generations and sold worldwide under various nameplates.
-
C.
Mazda SC
Mazda SC was a Japanese company football club owned by Mazda that later evolved into the professional J.League team Sanfrecce Hiroshima.
-
D.
Mazda Axela
The Mazda Axela is the name used in Japan for the Mazda3, a popular compact car known for its sporty handling and stylish design.
-
E.
Mazda 626
The Mazda 626 is a mid-size family car produced by the Japanese automaker Mazda from the late 1970s to the early 2000s, known for its practicality, reliability, and global popularity.
- 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_69d8dcfd05bc819088903cca13cc2846 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5c47f6c948190918ade08bb88f1fd |
completed | April 20, 2026, 6:15 a.m. |
Created at: April 10, 2026, 11:58 a.m.