Triple

T17315020
Position Surface form Disambiguated ID Type / Status
Subject Berrylands E420398 entity
Predicate hasElectoralWard P962 FINISHED
Object Berrylands ward
Berrylands ward is a local electoral division in the Royal Borough of Kingston upon Thames in southwest London, responsible for electing councillors to the borough council.
E1262008 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: Berrylands ward | Statement: [Berrylands, hasElectoralWard, Berrylands ward]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Berrylands ward
Context triple: [Berrylands, hasElectoralWard, Berrylands ward]
  • A. Hazeldean
    Hazeldean is a rural locality and small town situated within Queensland’s Somerset Region in Australia.
  • B. Blossom Village
    Blossom Village is the main settlement and population center on Little Cayman in the Cayman Islands.
  • C. Woodfieldside
    Woodfieldside is a small residential area in South Wales situated near the town of Blackwood in Caerphilly County Borough.
  • D. Devore Heights
    Devore Heights is a residential community in the foothills of the San Bernardino Mountains in Southern California.
  • E. Longlands
    Longlands is a suburban residential area in southeast London, known for its quiet streets, local schools, and proximity to green spaces.
  • 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: Berrylands ward
Triple: [Berrylands, hasElectoralWard, Berrylands ward]
Generated description
Berrylands ward is a local electoral division in the Royal Borough of Kingston upon Thames in southwest London, responsible for electing councillors to the borough council.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Berrylands ward
Target entity description: Berrylands ward is a local electoral division in the Royal Borough of Kingston upon Thames in southwest London, responsible for electing councillors to the borough council.
  • A. Hazeldean
    Hazeldean is a rural locality and small town situated within Queensland’s Somerset Region in Australia.
  • B. Blossom Village
    Blossom Village is the main settlement and population center on Little Cayman in the Cayman Islands.
  • C. Woodfieldside
    Woodfieldside is a small residential area in South Wales situated near the town of Blackwood in Caerphilly County Borough.
  • D. Devore Heights
    Devore Heights is a residential community in the foothills of the San Bernardino Mountains in Southern California.
  • E. Longlands
    Longlands is a suburban residential area in southeast London, known for its quiet streets, local schools, and proximity to green spaces.
  • 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_69d889d22b848190a4663d0b8f8f76e7 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e4399c6ad88190ba7fcf1d2d53171c completed April 19, 2026, 2:10 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0180e6e830819097b33d6b99232727 completed May 11, 2026, 7:10 a.m.
NEDg Description generation batch_6a01853590d081908f6523c55e4f610d completed May 11, 2026, 7:28 a.m.
NED2 Entity disambiguation (via description) batch_6a01860e39788190bbf5ca5188352d95 completed May 11, 2026, 7:32 a.m.
Created at: April 10, 2026, 5:43 a.m.