Triple
T7340792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guernsey law |
E169240
|
entity |
| Predicate | regulates |
P46
|
FINISHED |
| Object | Guernsey Bar |
E553843
|
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: Guernsey Bar | Statement: [Guernsey law, regulates, Guernsey Bar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Guernsey Bar Context triple: [Guernsey law, regulates, Guernsey Bar]
-
A.
Bar of Ireland
The Bar of Ireland is the professional body that regulates and represents barristers practicing at the independent bar in Ireland.
-
B.
Isle of Man Bar
The Isle of Man Bar is the professional body responsible for regulating and representing advocates (lawyers) practicing under Manx law on the Isle of Man.
-
C.
Bervie
Bervie is a civil parish in Aberdeenshire, Scotland, encompassing the coastal town of Inverbervie and its surrounding area.
-
D.
Kendal Mint Cake
Kendal Mint Cake is a traditional British glucose-based mint confection, famously used as an energy-boosting snack by mountaineers and hikers.
-
E.
Guernsey
chosen
Guernsey is a self-governing British Crown dependency in the English Channel, known for its distinct legal status, financial services industry, and dairy cattle breed.
- 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_69c68a57710481909f0c1f3c6ebdb6f2 |
completed | March 27, 2026, 1:47 p.m. |
| NER | Named-entity recognition | batch_69c6f0d89cd481908c8c2dbcb034b111 |
completed | March 27, 2026, 9:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7ef294f608190ae2ccd45a1ca213a |
completed | March 28, 2026, 3:09 p.m. |
Created at: March 27, 2026, 3:04 p.m.