Triple
T27726235
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Danube waterway system |
E699104
|
entity |
| Predicate | linkedByCanal |
P34005
|
FINISHED |
| Object | Rhine–Main–Danube Canal |
—
|
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: Rhine–Main–Danube Canal | Statement: [Danube waterway system, linkedByCanal, Rhine–Main–Danube Canal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: linkedByCanal Context triple: [Danube waterway system, linkedByCanal, Rhine–Main–Danube Canal]
-
A.
connectsViaCanal
chosen
Indicates that one entity is linked or joined to another by means of a canal.
-
B.
containsCanal
Indicates that one geographical or spatial entity has a canal located within its boundaries or interior.
-
C.
linkedNetwork
Indicates that two entities are connected through a shared or associated network relationship.
-
D.
linkedByCorridor
Indicates that two locations are directly connected to each other by a corridor.
-
E.
linkedRight
Indicates that one entity is directly connected or positioned to the right of another entity in a sequence or structure.
- 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_69ef591012dc8190a6f1ec994f9f7ff7 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f73ae120bc8190bff94d38d7a7a00d |
completed | May 3, 2026, 12:09 p.m. |
| PD | Predicate disambiguation | batch_69f73a38d0848190aa5139144b8561c6 |
completed | May 3, 2026, 12:06 p.m. |
Created at: April 27, 2026, 3:09 p.m.