Triple
T31744892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tilbury–Zeebrugge (freight) |
E810242
|
entity |
| Predicate | portInBelgium |
P172901
|
FINISHED |
| Object | Port of Zeebrugge |
—
|
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: Port of Zeebrugge | Statement: [Tilbury–Zeebrugge (freight), portInBelgium, Port of Zeebrugge]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: portInBelgium Context triple: [Tilbury–Zeebrugge (freight), portInBelgium, Port of Zeebrugge]
-
A.
positionInBelgium
Indicates that one entity occupies a specific geographic location within the territory of Belgium.
-
B.
passengerTrafficRankInBelgium
Indicates the relative position of an entity in terms of passenger traffic volume compared to other entities within Belgium.
-
C.
primaryPortNetherlands
Indicates that the referenced port serves as the main or principal port for activities related to the Netherlands.
-
D.
tierInBelgium
Indicates that an entity belongs to, is classified within, or operates at a specific tier or level in the context of Belgium.
-
E.
infrastructureManagerBelgium
Indicates that an entity serves as the infrastructure manager responsible for railway (or similar network) infrastructure in Belgium.
- 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_69f348e233cc819083b6695f70cd75d8 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b0d21dd08190a9883ff71c94c71c |
completed | May 3, 2026, 2:20 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
| PDg | Predicate description generation | batch_69f6afeaaef88190aefa97e83f8db906 |
completed | May 3, 2026, 2:16 a.m. |
Created at: April 30, 2026, 11:26 p.m.