Triple
T14376857
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tórshavn |
E356497
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Streymoy |
E143905
|
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: Streymoy | Statement: [Tórshavn, locatedIn, Streymoy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Streymoy Context triple: [Tórshavn, locatedIn, Streymoy]
-
A.
Streymoy
chosen
Streymoy is the largest and most populous island of the Faroe Islands, home to the capital city Tórshavn and the archipelago’s main political and economic activities.
-
B.
Suðuroy
Suðuroy is the southernmost of the Faroe Islands, known for its dramatic coastal cliffs, small fishing villages, and relatively remote, rugged landscape.
-
C.
Eysturoy
Eysturoy is the second-largest island of the Faroe Islands, known for its rugged mountains, fjords, and traditional fishing villages.
-
D.
Ærø
Ærø is a small Danish island in the Baltic Sea known for its picturesque coastal towns, historic architecture, and popular cycling and sailing routes.
-
E.
Rømø
Rømø is a Danish island in the Wadden Sea known for its expansive sandy beaches, coastal dunes, and popular holiday resorts.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de900949fc81909be0da1734c46645 |
completed | April 14, 2026, 7:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c5728fc819089ef3c7c34b10101 |
completed | May 8, 2026, 2:37 a.m. |
Created at: April 10, 2026, 1:16 a.m.