Triple
T21904392
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Michigan rail car ferries |
E540895
|
entity |
| Predicate | usedLoadingMethod |
P125096
|
FINISHED |
| Object | apron-type transfer bridges |
—
|
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: apron-type transfer bridges | Statement: [Lake Michigan rail car ferries, usedLoadingMethod, apron-type transfer bridges]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedLoadingMethod Context triple: [Lake Michigan rail car ferries, usedLoadingMethod, apron-type transfer bridges]
-
A.
hasLoadingMethod
chosen
Indicates that one entity uses or is associated with a particular method or process for loading something (e.g., data, resources, or content).
-
B.
usedSupplyMethod
Indicates that an entity employed a particular method or process to supply or deliver something.
-
C.
usedExperimentalMethod
Indicates that an entity employed a specific experimental method or technique in carrying out an action, study, or investigation.
-
D.
usesLaunchMethod
Indicates that one entity employs or applies a particular launch method to initiate or start another entity or process.
-
E.
loader
Indicates a relationship where an entity is responsible for loading or placing items, data, or resources into another system, container, or context.
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f121d4c0248190909172decd7cbc64 |
completed | April 28, 2026, 9:08 p.m. |
| PD | Predicate disambiguation | batch_69e6be9ebf4c8190892df1a8e1313f88 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 7:29 p.m.