Triple
T4370454
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hyundai Kona |
E98881
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Mazda CX-30 |
E396579
|
NE 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: Mazda CX-30 | Statement: [Hyundai Kona, competitor, Mazda CX-30]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mazda CX-30 Context triple: [Hyundai Kona, competitor, Mazda CX-30]
-
A.
Mazda CX-30
chosen
The Mazda CX-30 is a compact crossover SUV known for its sleek design, upscale interior, and engaging driving dynamics within Mazda’s lineup.
-
B.
Mazda CX-5
The Mazda CX-5 is a compact crossover SUV known for its stylish design, engaging driving dynamics, and efficient Skyactiv technology.
-
C.
Mazda3
The Mazda3 is a popular compact car known for its sporty handling, stylish design, and well-appointed interior.
-
D.
Mazda2
The Mazda2 is a subcompact car known for its agile handling, fuel efficiency, and stylish design, positioned as an affordable entry-level model in Mazda’s lineup.
-
E.
Mazda CX-9
The Mazda CX-9 is a mid-size three-row crossover SUV known for its stylish design, upscale interior, and engaging driving dynamics.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69b3454db3708190aeafd814413c4c3d |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3521cb7ec8190b7b79675871d97d8 |
completed | March 12, 2026, 11:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5e50bcc9481909b0b9d60198dce63 |
completed | March 14, 2026, 10:45 p.m. |
Created at: March 12, 2026, 11:17 p.m.