Triple

T5518162
Position Surface form Disambiguated ID Type / Status
Subject Poynton E144736 entity
Predicate roadNetworkFeature P3293 FINISHED
Object A523 London Road
A523 London Road is a major A-road in England that serves as a key route connecting Poynton with other towns in the region.
 E529696 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: A523 London Road | Statement: [Poynton, roadNetworkFeature, A523 London Road]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A523 London Road
Context triple: [Poynton, roadNetworkFeature, A523 London Road]
  • A. A57 Manchester Road
    A57 Manchester Road is a major road in northern England that forms part of the A57 route connecting Manchester with Sheffield and other surrounding areas.
  • B. Ealing Road Terrace
    Ealing Road Terrace is a traditional standing terrace section of Griffin Park, the former home stadium of Brentford Football Club in London.
  • C. 73 Harlow Street
    73 Harlow Street is the historic municipal building that serves as Bangor City Hall in Bangor, Maine.
  • D. Acorn Street
    Acorn Street is a famously picturesque, cobblestone residential lane in Boston often cited as one of the most photographed streets in the United States.
  • E. Vicarage Road
    Vicarage Road is a football stadium in Watford, England, best known as the long-time home ground of Watford F.C.
  • 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: A523 London Road
Triple: [Poynton, roadNetworkFeature, A523 London Road]
Generated description
A523 London Road is a major A-road in England that serves as a key route connecting Poynton with other towns in the region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A523 London Road
Target entity description: A523 London Road is a major A-road in England that serves as a key route connecting Poynton with other towns in the region.
  • A. A57 Manchester Road
    A57 Manchester Road is a major road in northern England that forms part of the A57 route connecting Manchester with Sheffield and other surrounding areas.
  • B. Ealing Road Terrace
    Ealing Road Terrace is a traditional standing terrace section of Griffin Park, the former home stadium of Brentford Football Club in London.
  • C. 73 Harlow Street
    73 Harlow Street is the historic municipal building that serves as Bangor City Hall in Bangor, Maine.
  • D. Acorn Street
    Acorn Street is a famously picturesque, cobblestone residential lane in Boston often cited as one of the most photographed streets in the United States.
  • E. Vicarage Road
    Vicarage Road is a football stadium in Watford, England, best known as the long-time home ground of Watford F.C.
  • 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_69c008f77ff88190b0cd50ca207295d1 completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01f6cefe48190bfda90d6afab8468 completed March 22, 2026, 4:57 p.m.
NED1 Entity disambiguation (via context triple) batch_69c027e1ed4c81908f670286556ced81 completed March 22, 2026, 5:33 p.m.
NEDg Description generation batch_69c03847b3348190be97b7c5795df368 completed March 22, 2026, 6:43 p.m.
NED2 Entity disambiguation (via description) batch_69c038e148a0819080a306307e60d437 completed March 22, 2026, 6:45 p.m.
Created at: March 22, 2026, 3:33 p.m.