Triple

T18006561
Position Surface form Disambiguated ID Type / Status
Subject HM Prison Saughton E430763 entity
Predicate locatedIn P40 FINISHED
Object Saughton
Saughton is a district in the west of Edinburgh, Scotland, known for its residential areas, public park, and the presence of a major prison.
E1301516 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: Saughton | Statement: [HM Prison Saughton, locatedIn, Saughton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Saughton
Context triple: [HM Prison Saughton, locatedIn, Saughton]
  • A. Gavinton
    Gavinton is a small village in the Scottish Borders region of Scotland, situated near the town of Duns.
  • B. Kirkcowan
    Kirkcowan is a small rural village in Dumfries and Galloway in southwest Scotland.
  • C. Longden
    Longden is an English-language surname borne by various notable individuals across fields such as politics, sports, and the arts.
  • D. Laurieston
    Laurieston is a district in Glasgow, Scotland, known for its central location near the River Clyde and mix of residential and urban redevelopment areas.
  • E. Balgowan
    Balgowan is a rural settlement in South Africa’s KwaZulu-Natal province, known for its scenic countryside, farms, and role in the Midlands Meander tourism route.
  • 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: Saughton
Triple: [HM Prison Saughton, locatedIn, Saughton]
Generated description
Saughton is a district in the west of Edinburgh, Scotland, known for its residential areas, public park, and the presence of a major prison.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Saughton
Target entity description: Saughton is a district in the west of Edinburgh, Scotland, known for its residential areas, public park, and the presence of a major prison.
  • A. Gavinton
    Gavinton is a small village in the Scottish Borders region of Scotland, situated near the town of Duns.
  • B. Kirkcowan
    Kirkcowan is a small rural village in Dumfries and Galloway in southwest Scotland.
  • C. Longden
    Longden is an English-language surname borne by various notable individuals across fields such as politics, sports, and the arts.
  • D. Laurieston
    Laurieston is a district in Glasgow, Scotland, known for its central location near the River Clyde and mix of residential and urban redevelopment areas.
  • E. Balgowan
    Balgowan is a rural settlement in South Africa’s KwaZulu-Natal province, known for its scenic countryside, farms, and role in the Midlands Meander tourism route.
  • 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_69d8b904530081908bf341d842464856 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4b51c7da48190ab70775a672e2d5f completed April 19, 2026, 10:57 a.m.
NED1 Entity disambiguation (via context triple) batch_6a03431d76ac819090f951b6f93aa665 completed May 12, 2026, 3:11 p.m.
NEDg Description generation batch_6a03448b74908190a9c0fadcfc4adbb4 completed May 12, 2026, 3:17 p.m.
NED2 Entity disambiguation (via description) batch_6a034552e424819087b23bcf3f688523 completed May 12, 2026, 3:20 p.m.
Created at: April 10, 2026, 10:24 a.m.