Triple

T12142705
Position Surface form Disambiguated ID Type / Status
Subject M55 motorway E289227 entity
Predicate hasJunction P1018 FINISHED
Object Junction 4
Junction 4 is a junction on England’s M55 motorway, serving as one of the key access points between the motorway and the local road network near Blackpool.
 E964319 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: Junction 4 | Statement: [M55 motorway, hasJunction, Junction 4]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Junction 4
Context triple: [M55 motorway, hasJunction, Junction 4]
  • A. Junction 6
    Junction 6 is an interchange on England’s M58 motorway connecting local roads to the regional motorway network.
  • B. Junction 7
    Junction 7 is a numbered junction on England’s M58 motorway, serving as one of the route’s access and exit points.
  • C. Junction 7
    Junction 7 is a numbered interchange on the M20 motorway in England, providing access between the motorway and the surrounding local road network.
  • D. Junction 1
    Junction 1 is a major road interchange on England’s M58 motorway, connecting it with local and regional routes.
  • E. Junction 1
    Junction 1 is a motorway interchange on the M20 in southeast England, providing access between the M20 and local roads near the London orbital 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: Junction 4
Triple: [M55 motorway, hasJunction, Junction 4]
Generated description
Junction 4 is a junction on England’s M55 motorway, serving as one of the key access points between the motorway and the local road network near Blackpool.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Junction 4
Target entity description: Junction 4 is a junction on England’s M55 motorway, serving as one of the key access points between the motorway and the local road network near Blackpool.
  • A. Junction 6
    Junction 6 is an interchange on England’s M58 motorway connecting local roads to the regional motorway network.
  • B. Junction 7
    Junction 7 is a numbered junction on England’s M58 motorway, serving as one of the route’s access and exit points.
  • C. Junction 7
    Junction 7 is a numbered interchange on the M20 motorway in England, providing access between the motorway and the surrounding local road network.
  • D. Junction 1
    Junction 1 is a major road interchange on England’s M58 motorway, connecting it with local and regional routes.
  • E. Junction 1
    Junction 1 is a motorway interchange on the M20 in southeast England, providing access between the M20 and local roads near the London orbital 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_69d6ab4c6710819097a9d228382dde43 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d915a9838081909622cc14df2a2582 completed April 10, 2026, 3:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69f5f69501348190a9ac090c7db37c20 completed May 2, 2026, 1:05 p.m.
NEDg Description generation batch_69f5ff815b748190932bfe163ea2847d completed May 2, 2026, 1:43 p.m.
NED2 Entity disambiguation (via description) batch_69f60185ce8c8190abe3b1f633aac55d completed May 2, 2026, 1:52 p.m.
Created at: April 8, 2026, 9:49 p.m.