Triple
T4187332
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Portland stone |
E88343
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Dorset |
E70212
|
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: Dorset | Statement: [Portland stone, locatedIn, Dorset]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dorset Context triple: [Portland stone, locatedIn, Dorset]
-
A.
Dorset
chosen
Dorset is a rural county on England’s south coast, known for its Jurassic Coast World Heritage Site, rolling countryside, and historic market towns.
-
B.
Devon
Devon is a county in South West England known for its rugged coastlines, moorland national parks, and historic seaside towns.
-
C.
Devon
Devon is a residential neighbourhood located within the city of Fredericton in New Brunswick, Canada.
-
D.
Somerset
Somerset is a historic county in South West England known for its rural landscapes, coastal areas, and cities such as Bath and Wells.
-
E.
Somerset
Somerset is a borough in southwestern Pennsylvania that serves as the county seat of Somerset County and a gateway to the scenic Laurel Highlands region.
- 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_69aed9477e8c81908bcb862d2db55b1d |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0325a82c8190849d8a828e2c7b44 |
completed | March 9, 2026, 5:28 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bd567a48b881908e4bfec70943eb60 |
completed | March 20, 2026, 2:15 p.m. |
Created at: March 9, 2026, 3:45 p.m.