Triple
T3925084
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Roewe |
E93255
|
entity |
| Predicate | hasModel |
P2390
|
FINISHED |
| Object | Roewe i5 |
E93255
|
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: Roewe i5 | Statement: [Roewe, hasModel, Roewe i5]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Roewe i5 Context triple: [Roewe, hasModel, Roewe i5]
-
A.
Roewe
chosen
Roewe is a Chinese automobile marque owned by SAIC Motor, known for producing a range of passenger cars and SUVs, including electric and plug-in hybrid models.
-
B.
Wuling Cortez
The Wuling Cortez is a compact multi-purpose vehicle (MPV) produced by SAIC-GM-Wuling for markets such as Indonesia, offering three-row seating and family-oriented practicality.
-
C.
Baojun RM-5
The Baojun RM-5 is a compact multi-purpose vehicle (MPV) produced by the Chinese automaker Baojun, known for its modern styling and family-oriented practicality.
-
D.
Baojun RC-6
The Baojun RC-6 is a mid-size fastback-style sedan produced by the Chinese automaker Baojun, positioned as an affordable, tech-focused family car.
-
E.
BYD Han
The BYD Han is a flagship mid-size luxury sedan from Chinese automaker BYD, known for its advanced plug-in hybrid and electric powertrains and high-tech features.
- 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_69aed96bfa1081908f7b30f2c647dee6 |
completed | March 9, 2026, 2:30 p.m. |
| NER | Named-entity recognition | batch_69aeed7f3cc881909464db1970ba39ae |
completed | March 9, 2026, 3:55 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b52873d5a881909c4c29f06b94a467 |
completed | March 14, 2026, 9:20 a.m. |
Created at: March 9, 2026, 3:23 p.m.