Triple
T15351005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Volkswagen plant Salzgitter |
E367049
|
entity |
| Predicate | logisticsMode |
P94644
|
FINISHED |
| Object | rail freight |
—
|
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: rail freight | Statement: [Volkswagen plant Salzgitter, logisticsMode, rail freight]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: logisticsMode Context triple: [Volkswagen plant Salzgitter, logisticsMode, rail freight]
-
A.
logisticsFeature
Indicates that something possesses a characteristic, capability, or function specifically related to logistics operations or processes.
-
B.
freightType
chosen
Indicates the category or mode of freight associated with a shipment or transport activity.
-
C.
logistics
Indicates the organization, coordination, and management of how resources, goods, or information are efficiently moved and handled between entities.
-
D.
typeOfHaulage
Indicates the kind or category of haulage service or transport operation associated with an entity.
-
E.
vehicleLoadingMethod
Indicates the method or process by which a vehicle is loaded with goods, passengers, or other cargo.
- 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_69d85a1355608190a6673ddb67231d54 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e290efc8190b22c95dcd3e5f57f |
completed | April 16, 2026, 1:40 a.m. |
| PD | Predicate disambiguation | batch_69deca991e5081908b0df3d1ee7d5338 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:17 a.m.