Triple
T13147094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Å i Lofoten |
E312367
|
entity |
| Predicate | connectedByRoadTo |
P11435
|
FINISHED |
| Object | Reine |
E312366
|
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: Reine | Statement: [Å i Lofoten, connectedByRoadTo, Reine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Reine Context triple: [Å i Lofoten, connectedByRoadTo, Reine]
-
A.
Reine
chosen
Reine is a picturesque fishing village in Norway’s Lofoten archipelago, known for its dramatic mountain backdrop and traditional red rorbuer cabins by the sea.
-
B.
Margrete
Margrete is a Scandinavian variant of the female given name Margaret, commonly used in Nordic countries.
-
C.
Karoline
Karoline is a feminine given name, commonly used in various European countries, that is a variant spelling of Caroline.
-
D.
Princess Tilde
Princess Tilde is a fictional European royal character from the "Kingsman" film series, portrayed by Swedish actress Hanna Alström.
-
E.
Princess of Neuchâtel
The Princess of Neuchâtel was the sovereign ruler of the Principality of Neuchâtel, a small but strategically important territory in what is now western Switzerland.
- 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_69d806aabde48190899e13e41659cae5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98bd0f5b08190ab700c5de1c8e138 |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6eae834908190aecb825db1d705ff |
completed | May 3, 2026, 6:27 a.m. |
Created at: April 9, 2026, 9:10 p.m.