Triple

T19430025
Position Surface form Disambiguated ID Type / Status
Subject Prince’s Garden E486085 entity
Predicate near P350 FINISHED
Object Isabel II Garden NE NERFINISHED

How this triple was built (2 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: Isabel II Garden | Statement: [Prince’s Garden, near, Isabel II Garden]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Isabel II Garden
Context triple: [Prince’s Garden, near, Isabel II Garden]
  • A. Isabel II Garden chosen
    Isabel II Garden is a historic landscaped garden within the Royal Palace of Aranjuez complex in Spain, known for its ornamental design, fountains, and tree-lined walks.
  • B. Queen Elizabeth Gardens
    Queen Elizabeth Gardens is a public park in Salisbury, England, known for its riverside lawns, floral displays, and views of Salisbury Cathedral.
  • C. Coronation Gardens
    Coronation Gardens is a public park and recreational green space located in the district of Leyton in East London.
  • D. Queen Mary's Gardens
    Queen Mary's Gardens is a renowned formal rose garden and public green space located within Regent's Park in central London.
  • E. Luxembourg Gardens
    Luxembourg Gardens is a famous public park in Paris known for its formal lawns, statues, fountains, and the Luxembourg Palace.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e8d688f881909c85104a62e09d8a completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6321c774881908ba5bde20abd5adc completed April 20, 2026, 2:03 p.m.
Created at: April 10, 2026, 1:37 p.m.