Triple
T33827183
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS Empress of Japan (1891) |
E866987
|
entity |
| Predicate | serviceEntryPort |
P192170
|
FINISHED |
| Object | Vancouver |
—
|
NE NERFINISHED |
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: Vancouver | Statement: [SS Empress of Japan (1891), serviceEntryPort, Vancouver]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: serviceEntryPort Context triple: [SS Empress of Japan (1891), serviceEntryPort, Vancouver]
-
A.
serviceEntryWith
Indicates that one entity is associated with or accompanied by a particular service entry in a joint or linked context.
-
B.
serviceModuleDockingPort
Indicates a docking connection between a service module and a docking port.
-
C.
serviceEntryInROC
Indicates that a service entry is recorded or included in a Register of Companies (ROC) or similar official registry.
-
D.
serviceEntryContext
Indicates the contextual circumstances or environment in which a particular service entry is created, recorded, or applied.
-
E.
serviceEntryRole
Indicates the role or function an entity performs in the context of providing or managing a particular service.
- F. None of above. chosen
Provenance (4 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_69f34991dd248190a659541588506b3c |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fcf825ca7081909d06b0df33eb33f9 |
completed | May 7, 2026, 8:37 p.m. |
| PD | Predicate disambiguation | batch_69fcf42160f0819096812a8bf590875e |
completed | May 7, 2026, 8:20 p.m. |
| PDg | Predicate description generation | batch_69fcf82405c88190a19cecf8e9cc272d |
completed | May 7, 2026, 8:37 p.m. |
Created at: May 1, 2026, 1:46 a.m.