Triple

T15306011
Position Surface form Disambiguated ID Type / Status
Subject Haslemere E365898 entity
Predicate hasRoad P959 FINISHED
Object A287
A287 is a regional road in England that serves as one of the main routes connecting the town of Haslemere to surrounding areas.
 E1150631 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: A287 | Statement: [Haslemere, hasRoad, A287]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: A287
Context triple: [Haslemere, hasRoad, A287]
  • A. A282
    A282 is a key section of the London orbital road network that links the M25 across the River Thames via the Dartford Crossing.
  • B. A286
    A286 is a regional road in southern England that connects the town of Haslemere with other nearby communities and routes.
  • C. A27
    A27 is a major east–west trunk road on the south coast of England, linking key towns and cities between East Sussex and Hampshire.
  • D. A298
    The A298 is a main road in southwest London that connects the Raynes Park area with other parts of the city’s road network.
  • E. A217
    The A217 is a major road in southern England that connects parts of London with Surrey, serving as an important route for local and regional traffic.
  • 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: A287
Triple: [Haslemere, hasRoad, A287]
Generated description
A287 is a regional road in England that serves as one of the main routes connecting the town of Haslemere to surrounding areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: A287
Target entity description: A287 is a regional road in England that serves as one of the main routes connecting the town of Haslemere to surrounding areas.
  • A. A282
    A282 is a key section of the London orbital road network that links the M25 across the River Thames via the Dartford Crossing.
  • B. A286 chosen
    A286 is a regional road in southern England that connects the town of Haslemere with other nearby communities and routes.
  • C. A27
    A27 is a major east–west trunk road on the south coast of England, linking key towns and cities between East Sussex and Hampshire.
  • D. A298
    The A298 is a main road in southwest London that connects the Raynes Park area with other parts of the city’s road network.
  • E. A217
    The A217 is a major road in southern England that connects parts of London with Surrey, serving as an important route for local and regional traffic.
  • F. None of above.

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_69d85a113ee881908e297a1d38dd79fa completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03ccef14c819099c5ebe962e7f867 completed April 16, 2026, 1:35 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff01e47d8c8190844d45dda9a3e5ea completed May 9, 2026, 9:44 a.m.
NEDg Description generation batch_69ff02ec353881909c7b7a7ba60d0dbc completed May 9, 2026, 9:48 a.m.
NED2 Entity disambiguation (via description) batch_69ff035170248190a9aca4345996c661 completed May 9, 2026, 9:50 a.m.
Created at: April 10, 2026, 3:16 a.m.