Triple
T6908641
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Borkum |
E159874
|
entity |
| Predicate | hasHarbor |
P3007
|
FINISHED |
| Object | Borkum harbor |
E159874
|
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: Borkum harbor | Statement: [Borkum, hasHarbor, Borkum harbor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Borkum harbor Context triple: [Borkum, hasHarbor, Borkum harbor]
-
A.
Borkum
chosen
Borkum is a German North Sea island known for its seaside resorts, sandy beaches, and role as the westernmost of the East Frisian Islands.
-
B.
Eemshaven
Eemshaven is a major seaport and energy hub in the north of the Netherlands, known for its power plants, data centers, and offshore wind connections.
-
C.
Holland harbor
Holland Harbor is a port on the eastern shore of Lake Michigan that serves the city of Holland, Michigan, providing access between Lake Macatawa and the open lake.
-
D.
Orkdal Harbor
Orkdal Harbor is a local port facility in Orkland municipality in Trøndelag, Norway, serving regional maritime transport and industry.
-
E.
Port of Flensburg
The Port of Flensburg is a small commercial and ferry harbor on the Flensburg Fjord near the German-Danish border, serving regional maritime trade and tourism.
- 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_69c68839ccb88190b4aa5cc1aca3448f |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6d9be98748190b5cb698e66e3aa42 |
completed | March 27, 2026, 7:25 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c749076f6c819088b0b40dd3e208b0 |
completed | March 28, 2026, 3:20 a.m. |
Created at: March 27, 2026, 2:25 p.m.