Triple
T14040870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | BMW E89 |
E337839
|
entity |
| Predicate | successorBodyStyleChange |
P112599
|
FINISHED |
| Object | returned to soft-top on G29 Z4 |
—
|
LITERAL 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: returned to soft-top on G29 Z4 | Statement: [BMW E89, successorBodyStyleChange, returned to soft-top on G29 Z4]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorBodyStyleChange Context triple: [BMW E89, successorBodyStyleChange, returned to soft-top on G29 Z4]
-
A.
successorBodyStyleLine
Indicates that one body style line directly follows and replaces another in a sequence or product lineage.
-
B.
replacedBodyType
Indicates that one body type has been substituted or superseded by another body type.
-
C.
secondGenerationBodyStyle
Indicates that the subject has or is associated with the second generation of a particular body style.
-
D.
offersBodyStyle
Indicates that an entity (such as a manufacturer or model line) makes a particular vehicle body style available as an option.
-
E.
successorBody
Indicates that one body or entity directly follows and replaces another in a sequence or succession.
- F. None of above. chosen
Provenance (4 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_69d81c664e48819088cbd8f433aeffe5 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de311814e48190adb637e1c97c0658 |
completed | April 14, 2026, 12:20 p.m. |
| PD | Predicate disambiguation | batch_69de05ab36b48190920efb1869bdb1fe |
completed | April 14, 2026, 9:15 a.m. |
| PDg | Predicate description generation | batch_69de2398856c81908bed6070e4ca6ab1 |
completed | April 14, 2026, 11:23 a.m. |
Created at: April 9, 2026, 10:20 p.m.