Triple

T18736758
Position Surface form Disambiguated ID Type / Status
Subject Basingstoke and Deane E458181 entity
Predicate hasVillage P4011 FINISHED
Object Silchester
Silchester is a small village in Hampshire, England, best known for the remains of the Roman town of Calleva Atrebatum.
E1340825 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: Silchester | Statement: [Basingstoke and Deane, hasVillage, Silchester]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Silchester
Context triple: [Basingstoke and Deane, hasVillage, Silchester]
  • A. Amesbury
    Amesbury is a historic town in Wiltshire, England, best known for its proximity to the prehistoric monument of Stonehenge.
  • B. Amesbury
    Amesbury is a historic New England city in northeastern Massachusetts known for its early shipbuilding and industrial heritage along the Merrimack River.
  • C. Romsey
    Romsey is a historic market town in Hampshire, England, known for its medieval abbey and riverside setting.
  • D. Durovernum Cantiacorum
    Durovernum Cantiacorum was the Roman-era name for the settlement that later became the English city of Canterbury, an important town in the Roman province of Britannia.
  • E. Viroconium Cornoviorum
    Viroconium Cornoviorum was a major Roman town in Roman Britain, located near modern Wroxeter in Shropshire and once one of the largest urban centres in the province.
  • 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: Silchester
Triple: [Basingstoke and Deane, hasVillage, Silchester]
Generated description
Silchester is a small village in Hampshire, England, best known for the remains of the Roman town of Calleva Atrebatum.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Silchester
Target entity description: Silchester is a small village in Hampshire, England, best known for the remains of the Roman town of Calleva Atrebatum.
  • A. Amesbury
    Amesbury is a historic town in Wiltshire, England, best known for its proximity to the prehistoric monument of Stonehenge.
  • B. Amesbury
    Amesbury is a historic New England city in northeastern Massachusetts known for its early shipbuilding and industrial heritage along the Merrimack River.
  • C. Romsey
    Romsey is a historic market town in Hampshire, England, known for its medieval abbey and riverside setting.
  • D. Durovernum Cantiacorum
    Durovernum Cantiacorum was the Roman-era name for the settlement that later became the English city of Canterbury, an important town in the Roman province of Britannia.
  • E. Viroconium Cornoviorum
    Viroconium Cornoviorum was a major Roman town in Roman Britain, located near modern Wroxeter in Shropshire and once one of the largest urban centres in the province.
  • 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_69d8d394dc308190b6725073f5db324c completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e57689fa508190ad821d361cba9edf completed April 20, 2026, 12:42 a.m.
NED1 Entity disambiguation (via context triple) batch_6a053261c074819081acb03dd7f8f62a completed May 14, 2026, 2:24 a.m.
NEDg Description generation batch_6a05369aa0488190b05cb5d1204db6d3 completed May 14, 2026, 2:42 a.m.
NED2 Entity disambiguation (via description) batch_6a053766f7b48190b3b01ee99b22f57d completed May 14, 2026, 2:45 a.m.
Created at: April 10, 2026, 11:51 a.m.