Triple
T16179305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MG Hector |
E392644
|
entity |
| Predicate | competitor |
P1375
|
FINISHED |
| Object | Kia Seltos |
E436816
|
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: Kia Seltos | Statement: [MG Hector, competitor, Kia Seltos]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kia Seltos Context triple: [MG Hector, competitor, Kia Seltos]
-
A.
Kia Seltos
chosen
The Kia Seltos is a compact crossover SUV known for its modern styling, tech-focused interior, and value-oriented positioning in the small SUV segment.
-
B.
Kia Sportage
The Kia Sportage is a compact crossover SUV known for its modern styling, practicality, and value-oriented features in the family SUV segment.
-
C.
Kia Soul
The Kia Soul is a compact crossover SUV known for its boxy design, spacious interior, and distinctive youthful styling.
-
D.
Kia K5
The Kia K5 is a mid-size family sedan known for its sleek styling, advanced technology features, and value-oriented positioning in Kia’s global lineup.
-
E.
Hyundai Kona
The Hyundai Kona is a subcompact crossover SUV produced by the South Korean automaker Hyundai, known for its distinctive styling, urban-friendly size, and availability with gasoline, hybrid, and electric powertrains.
- 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_69d87f1d32208190942e4e499a80c18c |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e2205b88b481908ecdd8d663dc668b |
completed | April 17, 2026, 11:58 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffff0022148190bc1810e76cf6d994 |
completed | May 10, 2026, 3:44 a.m. |
Created at: April 10, 2026, 5:02 a.m.