Triple

T5604890
Position Surface form Disambiguated ID Type / Status
Subject Buchan E147209 entity
Predicate containsSettlement P847 FINISHED
Object Mintlaw
Mintlaw is a village in Aberdeenshire, Scotland, known as a local service and administrative centre for the surrounding rural area.
E529873 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: Mintlaw | Statement: [Buchan, containsSettlement, Mintlaw]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mintlaw
Context triple: [Buchan, containsSettlement, Mintlaw]
  • A. Greenlaw
    Greenlaw is a small historic town in the Scottish Borders that once served as the county town of Berwickshire.
  • B. Lux et Lex
    Lux et Lex is the Latin motto of the University of North Dakota, traditionally interpreted as “Light and Law.”
  • C. Sweet & Maxwell
    Sweet & Maxwell is a prominent UK-based legal publisher known for producing authoritative law books, journals, and online legal information services.
  • D. Notman Law
    Notman Law is a notable geographical feature located within the Tweedsmuir Hills of southern Scotland.
  • E. Martindale
    Martindale is a remote, scenic valley in the Lake District of Cumbria, England, known for its rugged fells, red deer herd, and tranquil walking routes.
  • 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: Mintlaw
Triple: [Buchan, containsSettlement, Mintlaw]
Generated description
Mintlaw is a village in Aberdeenshire, Scotland, known as a local service and administrative centre for the surrounding rural area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mintlaw
Target entity description: Mintlaw is a village in Aberdeenshire, Scotland, known as a local service and administrative centre for the surrounding rural area.
  • A. Greenlaw
    Greenlaw is a small historic town in the Scottish Borders that once served as the county town of Berwickshire.
  • B. Lux et Lex
    Lux et Lex is the Latin motto of the University of North Dakota, traditionally interpreted as “Light and Law.”
  • C. Sweet & Maxwell
    Sweet & Maxwell is a prominent UK-based legal publisher known for producing authoritative law books, journals, and online legal information services.
  • D. Notman Law
    Notman Law is a notable geographical feature located within the Tweedsmuir Hills of southern Scotland.
  • E. Martindale
    Martindale is a remote, scenic valley in the Lake District of Cumbria, England, known for its rugged fells, red deer herd, and tranquil walking routes.
  • 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_69c0090500f881908374285baf0ac46f completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c020f9408481908cf006074c726301 completed March 22, 2026, 5:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0287649cc8190ae356790dd993973 completed March 22, 2026, 5:35 p.m.
NEDg Description generation batch_69c0350fdfec8190ad721167cde82a37 completed March 22, 2026, 6:29 p.m.
NED2 Entity disambiguation (via description) batch_69c0358474c88190a8a0fa209fbc6ddf completed March 22, 2026, 6:31 p.m.
Created at: March 22, 2026, 3:39 p.m.