Triple
T20633890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sound of Ulva |
E507025
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object | Staffa |
—
|
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: Staffa | Statement: [Sound of Ulva, hasNearbyIsland, Staffa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Staffa Context triple: [Sound of Ulva, hasNearbyIsland, Staffa]
-
A.
Staffa
Staffa is a small alpine hamlet that forms part of the mountain village and ski resort area of Macugnaga in northern Italy.
-
B.
Staffa
chosen
Staffa is a small uninhabited Scottish island in the Inner Hebrides, famed for its striking hexagonal basalt columns and the sea cave known as Fingal’s Cave.
-
C.
Stanna
"Stanna" is a musical number from the Swedish musical "Kristina från Duvemåla," known for its emotional depth and reflection on longing and belonging.
-
D.
Stallikon
Stallikon is a municipality in the canton of Zurich in Switzerland, situated in a hilly, forested area near Zurich and known for its rural character and natural landscapes.
-
E.
Stavenisse
Stavenisse is a small village in the Dutch province of Zeeland, located on the island of Tholen and known for its dike landscapes and fishing heritage.
- 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_69e0b4bd4a0081908d4e97a590a33fb2 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6ad0d808c81908a60abd02a22ed92 |
completed | April 20, 2026, 10:47 p.m. |
Created at: April 16, 2026, 11:42 a.m.