Triple
T19845859
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Corryvreckan whirlpool |
E476857
|
entity |
| Predicate | nearbyIsland |
P2064
|
FINISHED |
| Object | Lunga |
—
|
NE NERFINISHED |
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: Lunga | Statement: [Corryvreckan whirlpool, nearbyIsland, Lunga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lunga Context triple: [Corryvreckan whirlpool, nearbyIsland, Lunga]
-
A.
Lunga
chosen
Lunga is a Scottish island in the Treshnish Isles, known for its dramatic cliffs and large seabird colonies, especially puffins.
-
B.
Longo
Longo is an Italian surname borne by various notable figures in politics, arts, and sports.
-
C.
Longu
Longu is an Austronesian language spoken in the Solomon Islands, known primarily as a local name for the Longgu language.
-
D.
Loenga
Loenga is a small residential and industrial neighborhood in Oslo, Norway, situated near the railway yards and the Oslofjord.
-
E.
Lange
Lange is a German surname borne by numerous notable individuals across fields such as science, politics, arts, and sports.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51d39d081909bcfafeaaf3d2fcc |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e658091c608190b4eb9bcedd88e147 |
completed | April 20, 2026, 4:44 p.m. |
Created at: April 10, 2026, 1:51 p.m.