Triple

T22736403
Position Surface form Disambiguated ID Type / Status
Subject Gosport Peninsula E562282 entity
Predicate hasSettlement P1068 FINISHED
Object Bridgemary
Bridgemary is a residential suburb within the town of Gosport in Hampshire, England.
E1552380 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: Bridgemary | Statement: [Gosport Peninsula, hasSettlement, Bridgemary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bridgemary
Context triple: [Gosport Peninsula, hasSettlement, Bridgemary]
  • A. Marian Maudsley
    Marian Maudsley is a central figure in L.P. Hartley’s novel "The Go-Between," an upper-class young woman whose secret romantic entanglement drives the story’s themes of class, innocence, and betrayal.
  • B. Caroline Biggerstaff
    Caroline Biggerstaff is an editor known for her work on the publication "True Stories."
  • C. Cicely Evans
    Cicely Evans is best known as the wife of American actor and diplomat John Gavin.
  • D. Elizabeth Marsh
    Elizabeth Marsh was the wife of American engineer Willis Carrier, the inventor widely credited with creating modern air conditioning.
  • E. Louisa Rix
    Louisa Rix is a British actress known for her work in television, film, and theatre, including roles in popular UK comedies.
  • 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: Bridgemary
Triple: [Gosport Peninsula, hasSettlement, Bridgemary]
Generated description
Bridgemary is a residential suburb within the town of Gosport in Hampshire, England.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bridgemary
Target entity description: Bridgemary is a residential suburb within the town of Gosport in Hampshire, England.
  • A. Marian Maudsley
    Marian Maudsley is a central figure in L.P. Hartley’s novel "The Go-Between," an upper-class young woman whose secret romantic entanglement drives the story’s themes of class, innocence, and betrayal.
  • B. Caroline Biggerstaff
    Caroline Biggerstaff is an editor known for her work on the publication "True Stories."
  • C. Cicely Evans
    Cicely Evans is best known as the wife of American actor and diplomat John Gavin.
  • D. Elizabeth Marsh
    Elizabeth Marsh was the wife of American engineer Willis Carrier, the inventor widely credited with creating modern air conditioning.
  • E. Louisa Rix
    Louisa Rix is a British actress known for her work in television, film, and theatre, including roles in popular UK comedies.
  • 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_69e24550859c81908727d91efc3a81b4 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1796fc2a88190a4d86b421345b088 completed April 29, 2026, 3:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0b8fcc0f7881908e1579bae911c3b6 completed May 18, 2026, 10:16 p.m.
NEDg Description generation batch_6a0b91253b5c8190b7fc62f7524017e6 completed May 18, 2026, 10:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0b91cbb52481909d0b092475aa4d36 completed May 18, 2026, 10:25 p.m.
Created at: April 17, 2026, 3:22 p.m.