Triple
T12140474
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 323 series EMU |
E289167
|
entity |
| Predicate | carLayout |
P70594
|
FINISHED |
| Object | longitudinal seating in most cars |
—
|
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: longitudinal seating in most cars | Statement: [323 series EMU, carLayout, longitudinal seating in most cars]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: carLayout Context triple: [323 series EMU, carLayout, longitudinal seating in most cars]
-
A.
vehicleLayout
Indicates how the components or seating within a vehicle are arranged or configured relative to each other.
-
B.
chassisConstruction
Indicates how the chassis of an object is built or assembled, specifying the construction method or structural design used.
-
C.
carBodyStyle
Indicates the specific body configuration or design style that characterizes a car (e.g., sedan, hatchback, SUV).
-
D.
hasVehicleDeck
Indicates that something (typically a vessel or structure) includes a dedicated deck or level designed for carrying or transporting vehicles.
-
E.
hasLongitudinalSeating
chosen
Indicates that an entity features seating arranged lengthwise along its sides rather than across its width.
- F. None of above.
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_69d6ab4c6710819097a9d228382dde43 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d91841615c819097f20a7447a1b8f4 |
completed | April 10, 2026, 3:33 p.m. |
| PD | Predicate disambiguation | batch_69d91508f8008190b3a90ec0bf0953ca |
completed | April 10, 2026, 3:19 p.m. |
Created at: April 8, 2026, 9:49 p.m.