Triple

T17732882
Position Surface form Disambiguated ID Type / Status
Subject Moto Hospitality E442631 entity
Predicate brandPortfolio P12124 FINISHED
Object Greggs
Greggs is a popular UK-based bakery and food-on-the-go chain known for its pastries, sausage rolls, and affordable snacks.
E1285069 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: Greggs | Statement: [Moto Hospitality, brandPortfolio, Greggs]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Greggs
Context triple: [Moto Hospitality, brandPortfolio, Greggs]
  • A. Farrells
    Farrells is an international architecture and urban design firm founded by British architect Sir Terry Farrell, known for its innovative and often postmodern projects.
  • B. Starbeck
    Starbeck is a suburb and railway district of Harrogate in North Yorkshire, England, known historically for its railway junction and associated industry.
  • C. Panera Bread
    Panera Bread is a popular American fast-casual restaurant and bakery chain known for its soups, salads, sandwiches, and freshly baked bread.
  • D. Ganmain Bakery
    Ganmain Bakery is a well-known country bakery in Ganmain, New South Wales, Australia, famed for its traditional meat pies often referred to as "Ganmain pies."
  • E. Baker’s
    Baker’s is a regional American supermarket chain known for offering a full range of groceries and household goods.
  • 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: Greggs
Triple: [Moto Hospitality, brandPortfolio, Greggs]
Generated description
Greggs is a popular UK-based bakery and food-on-the-go chain known for its pastries, sausage rolls, and affordable snacks.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Greggs
Target entity description: Greggs is a popular UK-based bakery and food-on-the-go chain known for its pastries, sausage rolls, and affordable snacks.
  • A. Farrells
    Farrells is an international architecture and urban design firm founded by British architect Sir Terry Farrell, known for its innovative and often postmodern projects.
  • B. Starbeck
    Starbeck is a suburb and railway district of Harrogate in North Yorkshire, England, known historically for its railway junction and associated industry.
  • C. Panera Bread
    Panera Bread is a popular American fast-casual restaurant and bakery chain known for its soups, salads, sandwiches, and freshly baked bread.
  • D. Ganmain Bakery
    Ganmain Bakery is a well-known country bakery in Ganmain, New South Wales, Australia, famed for its traditional meat pies often referred to as "Ganmain pies."
  • E. Baker’s
    Baker’s is a regional American supermarket chain known for offering a full range of groceries and household goods.
  • 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e478e86f188190a5dd7fb32fd04c7b completed April 19, 2026, 6:40 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0242f577ac8190bc6c258ed79c0f3f completed May 11, 2026, 8:58 p.m.
NEDg Description generation batch_6a024432dae081908718b4d9fa156858 completed May 11, 2026, 9:03 p.m.
NED2 Entity disambiguation (via description) batch_6a0244ad73388190b5b99ccbbd357d77 completed May 11, 2026, 9:05 p.m.
Created at: April 10, 2026, 10:08 a.m.