Triple
T1003301
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Auto Train |
E21650
|
entity |
| Predicate | hasDisembarkationProcess |
P18240
|
FINISHED |
| Object | vehicle unloading after arrival |
—
|
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: vehicle unloading after arrival | Statement: [Auto Train, hasDisembarkationProcess, vehicle unloading after arrival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDisembarkationProcess Context triple: [Auto Train, hasDisembarkationProcess, vehicle unloading after arrival]
-
A.
hasCustomsAndImmigration
Indicates that customs and immigration control services are present or provided at a given location or facility.
-
B.
hasPassengerHandling
chosen
Indicates that an entity is responsible for or involved in managing the processes and services related to handling passengers.
-
C.
hasBoardingType
Indicates the specific manner or method by which an entity is boarded or accessed (e.g., how passengers or items are taken on).
-
D.
hasPassengerTerminal
Indicates that one entity possesses or is equipped with a passenger terminal used for boarding, alighting, or handling passengers.
-
E.
hasCargoTerminal
Indicates that a location or facility includes or is equipped with a cargo terminal for handling freight.
- 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_69a493c53e648190ae8cb76c433fd9a7 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b4fe0a548190aee8abf1890e141e |
completed | March 1, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69a4b2b1f4f88190822598cfd2a0fd2b |
completed | March 1, 2026, 9:42 p.m. |
Created at: March 1, 2026, 7:41 p.m.