Triple
T14002008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boknafjorden |
E336848
|
entity |
| Predicate | hasIsland |
P970
|
FINISHED |
| Object | Utsira |
E486948
|
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: Utsira | Statement: [Boknafjorden, hasIsland, Utsira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Utsira Context triple: [Boknafjorden, hasIsland, Utsira]
-
A.
Utsira
chosen
Utsira is a small Norwegian island municipality in Rogaland county, known for its remote North Sea location, birdlife, and historic lighthouse.
-
B.
Kurima-jima
Kurima-jima is a small inhabited island in Okinawa Prefecture, Japan, known for its scenic beaches, coral reefs, and the Kurima Bridge connecting it to Miyako-jima.
-
C.
Tarutao Island
Tarutao Island is a rugged, largely undeveloped island in the Andaman Sea known for its national park status, rich marine life, and historical use as a prison colony.
-
D.
Okinoerabu Island
Okinoerabu Island is a remote coral island in Japan’s Amami archipelago, known for its extensive limestone caves, subtropical climate, and agriculture, particularly lily and sugarcane cultivation.
-
E.
Sakishima Island
Sakishima Island is a man-made island in Osaka, Japan, known as a major business and commercial district featuring high-rise buildings and convention facilities.
- 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_69d81c645c5c8190b1fd16a285a1b78a |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2ed06a50819093ddc64f55050689 |
completed | April 14, 2026, 12:10 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a011b2fc8f88190b9bd2887149e3d68 |
completed | May 10, 2026, 11:56 p.m. |
Created at: April 9, 2026, 10:19 p.m.