Triple
T1073512
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orkney Mainland |
E23382
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Stromness
Stromness is a historic harbor town on the southwest coast of Orkney Mainland in Scotland, known for its stone-built waterfront and maritime heritage.
|
E144093
|
NE FINISHED |
How this triple was built (4 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: Stromness | Statement: [Orkney Mainland, hasSettlement, Stromness]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Stromness Context triple: [Orkney Mainland, hasSettlement, Stromness]
-
A.
Sallands
Sallands is a Dutch Low Saxon dialect spoken in the Salland region of the province of Overijssel in the Netherlands.
-
B.
Kirkwall
Kirkwall is the largest town and administrative capital of Orkney in Scotland, known for its historic St Magnus Cathedral and Viking heritage.
-
C.
Carbisdale
Carbisdale is a location in Scotland best known as the site of a decisive 1650 battle during the Third English Civil War.
-
D.
Sanday
Sanday is one of the Orkney Islands of Scotland, known for its long sandy beaches, low-lying fertile farmland, and important archaeological sites.
-
E.
Hvalsey
Hvalsey is the best-preserved Norse ruin site in Greenland, known for its stone church and remnants of a medieval farming settlement.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Stromness Triple: [Orkney Mainland, hasSettlement, Stromness]
Generated description
Stromness is a historic harbor town on the southwest coast of Orkney Mainland in Scotland, known for its stone-built waterfront and maritime heritage.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Stromness Target entity description: Stromness is a historic harbor town on the southwest coast of Orkney Mainland in Scotland, known for its stone-built waterfront and maritime heritage.
-
A.
Sallands
Sallands is a Dutch Low Saxon dialect spoken in the Salland region of the province of Overijssel in the Netherlands.
-
B.
Kirkwall
Kirkwall is the largest town and administrative capital of Orkney in Scotland, known for its historic St Magnus Cathedral and Viking heritage.
-
C.
Carbisdale
Carbisdale is a location in Scotland best known as the site of a decisive 1650 battle during the Third English Civil War.
-
D.
Sanday
Sanday is one of the Orkney Islands of Scotland, known for its long sandy beaches, low-lying fertile farmland, and important archaeological sites.
-
E.
Hvalsey
Hvalsey is the best-preserved Norse ruin site in Greenland, known for its stone church and remnants of a medieval farming settlement.
- F. None of above. chosen
Provenance (5 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_69a493ee1f908190992b5f0d1b04459b |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b92afad88190b7705923f71fc760 |
completed | March 1, 2026, 10:09 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac93ad5644819095868c520c33cd83 |
completed | March 7, 2026, 9:07 p.m. |
| NEDg | Description generation | batch_69ac9569cba081909fda971f4dfde00a |
completed | March 7, 2026, 9:15 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac95da6e7c8190a0a719aa9c9f7a51 |
completed | March 7, 2026, 9:17 p.m. |
Created at: March 1, 2026, 7:42 p.m.