Triple

T15775163
Position Surface form Disambiguated ID Type / Status
Subject Machars E382470 entity
Predicate containsSettlement P847 FINISHED
Object Elrig
Elrig is a small rural settlement located in the Machars peninsula of Dumfries and Galloway in southwest Scotland.
E1175661 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: Elrig | Statement: [Machars, containsSettlement, Elrig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elrig
Context triple: [Machars, containsSettlement, Elrig]
  • A. Lyfjaberg
    Lyfjaberg is the mythological healing mountain associated with the Norse goddess Eir, often depicted as a place of cures and protection.
  • B. Rognon
    Rognon is a river in northeastern France that flows through the Haute-Marne department and serves as a tributary within the Marne river basin.
  • C. Arvegil
    Arvegil is a fictional Dúnedain king of Arnor in J.R.R. Tolkien’s legendarium, descended from Isildur.
  • D. Urstein
    Urstein is a locality in the municipality of Puch bei Hallein in the Austrian state of Salzburg, known for hosting the Salzburg University of Applied Sciences campus.
  • E. Maross
    Maross is a surname most notably associated with American actor Joe Maross, known for his work in mid-20th-century film and television.
  • 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: Elrig
Triple: [Machars, containsSettlement, Elrig]
Generated description
Elrig is a small rural settlement located in the Machars peninsula of Dumfries and Galloway in southwest Scotland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elrig
Target entity description: Elrig is a small rural settlement located in the Machars peninsula of Dumfries and Galloway in southwest Scotland.
  • A. Lyfjaberg
    Lyfjaberg is the mythological healing mountain associated with the Norse goddess Eir, often depicted as a place of cures and protection.
  • B. Rognon
    Rognon is a river in northeastern France that flows through the Haute-Marne department and serves as a tributary within the Marne river basin.
  • C. Arvegil
    Arvegil is a fictional Dúnedain king of Arnor in J.R.R. Tolkien’s legendarium, descended from Isildur.
  • D. Urstein
    Urstein is a locality in the municipality of Puch bei Hallein in the Austrian state of Salzburg, known for hosting the Salzburg University of Applied Sciences campus.
  • E. Maross
    Maross is a surname most notably associated with American actor Joe Maross, known for his work in mid-20th-century film and television.
  • 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_69d86da09a10819082fe9797b23e4664 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e05198c1588190a65e23c18443eb5c completed April 16, 2026, 3:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff877e67b881908a67b9acc79d998f completed May 9, 2026, 7:14 p.m.
NEDg Description generation batch_69ff88358e408190a8d7424fc495d4fa completed May 9, 2026, 7:17 p.m.
NED2 Entity disambiguation (via description) batch_69ff88f192a08190acbc2c3fc98c65c8 completed May 9, 2026, 7:20 p.m.
Created at: April 10, 2026, 4:47 a.m.