Triple
T13287338
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sullom Voe |
E316476
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Mavis Grind |
E1027613
|
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: Mavis Grind | Statement: [Sullom Voe, locatedNear, Mavis Grind]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mavis Grind Context triple: [Sullom Voe, locatedNear, Mavis Grind]
-
A.
Mavis Grind
chosen
Mavis Grind is a narrow isthmus in Northmavine, Shetland, known for nearly connecting the Atlantic Ocean and the North Sea at one of their closest points.
-
B.
Mavis
Mavis is a character in Enid Blyton’s "Malory Towers" series, known as a talented but vain singer whose ambition often leads her into trouble.
-
C.
Mavis
Mavis is a central character in the animated Hotel Transylvania film series, known as Dracula’s spirited and independent vampire daughter.
-
D.
Mavis
Mavis is a fictional character who appears in the crime novel "The Drowning Pool."
-
E.
Mavis
Mavis is the Allied reporting name for the Kawanishi H6K, a Japanese World War II-era flying boat used primarily for maritime patrol and reconnaissance.
- 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_69d806b349908190a9a61dd9323bf153 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99076aeec8190b0cb883ab60d3f6b |
completed | April 11, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f716d26a548190be15872154c9a942 |
completed | May 3, 2026, 9:35 a.m. |
Created at: April 9, 2026, 9:27 p.m.