Triple

T8000248
Position Surface form Disambiguated ID Type / Status
Subject Sonning Common E186228 entity
Predicate locatedNear P294 FINISHED
Object Caversham
Caversham is a suburban area of Reading in Berkshire, England, known for its riverside setting on the north bank of the River Thames.
E704090 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: Caversham | Statement: [Sonning Common, locatedNear, Caversham]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Caversham
Context triple: [Sonning Common, locatedNear, Caversham]
  • A. Calder Vale
    Calder Vale is a small rural village in Lancashire, England, known for its historic mill and picturesque setting in the Forest of Bowland.
  • B. Parrs Wood
    Parrs Wood is an area in south Manchester, England, known for its large entertainment and leisure complex and the historic Parrs Wood High School.
  • C. Edgemead
    Edgemead is a planned residential suburb in the northern part of Cape Town, South Africa, known for its garden-city layout and family-oriented community.
  • D. Adcote
    Adcote is a Victorian country house in Shropshire, England, designed in the late 19th century by architect Richard Norman Shaw in a distinctive Tudor Revival style.
  • E. Banwell
    Banwell is a village and civil parish in North Somerset, England, known for its historic caves and medieval architecture.
  • 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: Caversham
Triple: [Sonning Common, locatedNear, Caversham]
Generated description
Caversham is a suburban area of Reading in Berkshire, England, known for its riverside setting on the north bank of the River Thames.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Caversham
Target entity description: Caversham is a suburban area of Reading in Berkshire, England, known for its riverside setting on the north bank of the River Thames.
  • A. Calder Vale
    Calder Vale is a small rural village in Lancashire, England, known for its historic mill and picturesque setting in the Forest of Bowland.
  • B. Parrs Wood
    Parrs Wood is an area in south Manchester, England, known for its large entertainment and leisure complex and the historic Parrs Wood High School.
  • C. Edgemead
    Edgemead is a planned residential suburb in the northern part of Cape Town, South Africa, known for its garden-city layout and family-oriented community.
  • D. Adcote
    Adcote is a Victorian country house in Shropshire, England, designed in the late 19th century by architect Richard Norman Shaw in a distinctive Tudor Revival style.
  • E. Banwell
    Banwell is a village and civil parish in North Somerset, England, known for its historic caves and medieval architecture.
  • 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_69ca82aaaf24819084b94d18f699ba53 completed March 30, 2026, 2:03 p.m.
NER Named-entity recognition batch_69cb3c9b67988190a8a4a2c960017400 completed March 31, 2026, 3:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69cbe114372c819086f06e184d5ebde2 completed March 31, 2026, 2:58 p.m.
NEDg Description generation batch_69cbe441b76881909efa791b74316088 completed March 31, 2026, 3:12 p.m.
NED2 Entity disambiguation (via description) batch_69cc34749ae08190a1d30919a0594bfd completed March 31, 2026, 8:54 p.m.
Created at: March 30, 2026, 5:17 p.m.