Triple
T8480902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jumbo Mark II-class ferry |
E200514
|
entity |
| Predicate | vehicleLoadingMethod |
P82844
|
FINISHED |
| Object | drive-on/drive-off |
—
|
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: drive-on/drive-off | Statement: [Jumbo Mark II-class ferry, vehicleLoadingMethod, drive-on/drive-off]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vehicleLoadingMethod Context triple: [Jumbo Mark II-class ferry, vehicleLoadingMethod, drive-on/drive-off]
-
A.
cargoLoading
Indicates the action or process of placing cargo onto a vehicle, vessel, or other transport medium for shipment or movement.
-
B.
cargoVehicle
Indicates a relationship where a vehicle is used or designated for transporting cargo or goods.
-
C.
cargoAccess
Indicates that an entity has permission or capability to access, enter, or interact with a cargo area or cargo-related contents.
-
D.
cargoCapacityFeature
Indicates that an entity has a feature specifying how much cargo it can carry or accommodate.
-
E.
towingCapability
Indicates the maximum load or object weight that one entity is able to pull or tow.
- 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_69ca831b17988190a1f3f3413d57b820 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe5245034819088c7c5c40170c020 |
completed | March 31, 2026, 3:15 p.m. |
| PD | Predicate disambiguation | batch_69cbd104250c8190b4c499dcc9937494 |
completed | March 31, 2026, 1:49 p.m. |
| PDg | Predicate description generation | batch_69cbe12dd0b88190a38ec4d15dcc870b |
completed | March 31, 2026, 2:58 p.m. |
Created at: March 30, 2026, 6:12 p.m.