Triple
T11101888
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Lakes Maritime Academy |
E262527
|
entity |
| Predicate | trainsForIndustry |
P14268
|
FINISHED |
| Object | Great Lakes shipping industry |
—
|
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: Great Lakes shipping industry | Statement: [Great Lakes Maritime Academy, trainsForIndustry, Great Lakes shipping industry]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trainsForIndustry Context triple: [Great Lakes Maritime Academy, trainsForIndustry, Great Lakes shipping industry]
-
A.
trainsForOccupation
chosen
Indicates that an entity undergoes training or preparation aimed at qualifying for or performing a specific occupation.
-
B.
trainsCategory
Indicates that one entity is a category or type under which the other entity is trained or classified.
-
C.
trains
Indicates that one entity teaches, instructs, or coaches another entity to develop skills, knowledge, or abilities.
-
D.
maintainsTrainsFor
Indicates that one entity is responsible for servicing, repairing, or otherwise keeping trains operational for another entity.
-
E.
trainsOn
Indicates that one entity receives training, instruction, or practice using or based on another entity (such as a resource, dataset, tool, or subject).
- 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_69d6aa9a40d88190a373e2c7e48285db |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d79a2ab09081908ffce2df8912b657 |
completed | April 9, 2026, 12:23 p.m. |
| PD | Predicate disambiguation | batch_69d7441aa3548190b92dbde57841c135 |
completed | April 9, 2026, 6:15 a.m. |
Created at: April 8, 2026, 9:27 p.m.