Triple
T4284016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port of Rotterdam |
E97221
|
entity |
| Predicate | hasFacility |
P105
|
FINISHED |
| Object | Waalhaven |
E428010
|
NE 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: Waalhaven | Statement: [Port of Rotterdam, hasFacility, Waalhaven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waalhaven Context triple: [Port of Rotterdam, hasFacility, Waalhaven]
-
A.
Vechta
Vechta is a town in Lower Saxony, Germany, known for its historical significance, university, and annual Stoppelmarkt fair.
-
B.
Nieuwe Waterweg
Nieuwe Waterweg is a major artificial ship canal in the Netherlands that provides a direct deep-water connection between the North Sea and the port of Rotterdam.
-
C.
Hoendiep
Hoendiep is a canal in the Dutch province of Groningen that serves as an important regional waterway and transport route.
-
D.
Eemhaven
chosen
Eemhaven is a major container and short-sea shipping terminal area within the Port of Rotterdam in the Netherlands.
-
E.
Haringvliet
Haringvliet is a former estuary in the western Netherlands that now functions as a controlled waterway and nature area connecting the Rhine-Meuse river system to the North Sea.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69b3454595848190a0e6bbb6a2bea040 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3503c062c81908f9a9eeab5381ec9 |
completed | March 12, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b5d06ccbf081908bc23b5f194b9587 |
completed | March 14, 2026, 9:17 p.m. |
Created at: March 12, 2026, 11:07 p.m.