Triple
T31765150
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sylt Shuttle |
E810785
|
entity |
| Predicate | alsoTransports |
P2059
|
FINISHED |
| Object | car drivers and passengers |
—
|
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: car drivers and passengers | Statement: [Sylt Shuttle, alsoTransports, car drivers and passengers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: alsoTransports Context triple: [Sylt Shuttle, alsoTransports, car drivers and passengers]
-
A.
transports
chosen
Indicates that one entity carries or conveys another entity from one place to another.
-
B.
isTransport
Indicates that one entity serves as a means or method for conveying or carrying another entity from one place to another.
-
C.
hasTransporters
Indicates that one entity possesses, provides, or is equipped with one or more means of transportation for another entity or purpose.
-
D.
transportAssociated
Indicates an association between entities where one is involved in, related to, or characterized by the transport or movement of the other.
-
E.
transportInterface
Indicates a relationship where one entity serves as the medium or mechanism through which another entity is transported or conveyed.
- 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_69f348e463e08190b902d4819195e1f0 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6abaadc0c8190babed41feb5c15a6 |
completed | May 3, 2026, 1:58 a.m. |
| PD | Predicate disambiguation | batch_69f6aa21f2508190a204a424ffc00ca6 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 30, 2026, 11:32 p.m.