Triple
T20263211
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beinn Scalpaigh |
E498896
|
entity |
| Predicate | locatedOn |
P40
|
FINISHED |
| Object | Scalpay |
—
|
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: Scalpay | Statement: [Beinn Scalpaigh, locatedOn, Scalpay]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Scalpay Context triple: [Beinn Scalpaigh, locatedOn, Scalpay]
-
A.
Scalpay
chosen
Scalpay is a small inhabited island in the Outer Hebrides of Scotland, known for its rugged coastline, fishing heritage, and scenic views across the surrounding sea.
-
B.
Skales
Skales is a Nigerian rapper and singer known for his energetic Afropop and hip-hop tracks and for being part of the contemporary Nigerian music scene.
-
C.
Ycidra Money
Ycidra Money is an individual known by the nickname "Cee" Money.
-
D.
Squant
Squant is a figure from Wampanoag and related Indigenous mythologies, known primarily as the wife of the culture hero and giant Moshup.
-
E.
Bazmark
Bazmark is an Australian film production company founded by director Baz Luhrmann, known for visually lavish and stylistically distinctive movies such as "Moulin Rouge!" and "The Great Gatsby."
- 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_69da6275fa6c8190952924930adee150 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e674ccff008190920b418f51dc4311 |
completed | April 20, 2026, 6:47 p.m. |
Created at: April 11, 2026, 11:41 p.m.