Triple
T12813974
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fehmarn Belt |
E306342
|
entity |
| Predicate | plannedFixedLinkType |
P20417
|
FINISHED |
| Object | immersed tunnel |
—
|
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: immersed tunnel | Statement: [Fehmarn Belt, plannedFixedLinkType, immersed tunnel]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: plannedFixedLinkType Context triple: [Fehmarn Belt, plannedFixedLinkType, immersed tunnel]
-
A.
typicalLinkType
Indicates that one entity is the standard or most commonly used type of link associated with another entity.
-
B.
linkType
chosen
Indicates the specific kind or category of relationship that connects two linked entities.
-
C.
plannedStructure
Indicates that one entity is a structure that is intended or designed to be built or established in the future, rather than already existing.
-
D.
plannedVia
Indicates that something is arranged, organized, or scheduled by means of a particular method, process, or intermediary.
-
E.
plannedUnder
Indicates that one entity has been scheduled, organized, or arranged to occur within the scope, authority, or framework of another entity.
- 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_69d7bdf46c448190b1faa55aaacb6317 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96e9adcf08190a12801adcc613477 |
completed | April 10, 2026, 9:41 p.m. |
| PD | Predicate disambiguation | batch_69d9640ed7448190b276e7fab649f7d2 |
completed | April 10, 2026, 8:56 p.m. |
Created at: April 9, 2026, 5:31 p.m.