Triple

T4006749
Position Surface form Disambiguated ID Type / Status
Subject Richmond Palace E89542 entity
Predicate near P350 FINISHED
Object Richmond Green E249121 NE FINISHED

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: Richmond Green | Statement: [Richmond Palace, near, Richmond Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Richmond Green
Context triple: [Richmond Palace, near, Richmond Green]
  • A. Richmond Green chosen
    Richmond Green is a historic open space and recreational common in Richmond, London, known for its picturesque setting, cricket matches, and surrounding period architecture.
  • B. Brook Green
    Brook Green is a public park and residential area in the Hammersmith district of West London, known for its tree-lined green space and surrounding Victorian and Edwardian housing.
  • C. Hough Green
    Hough Green is a suburban area in Widnes, Cheshire, England, served by its own railway station and characterized by residential neighborhoods and local amenities.
  • D. Peartree Green
    Peartree Green is a historic open space and local nature area in the Woolston district of Southampton, known for its greenery and community recreation.
  • E. Englefield Green
    Englefield Green is a village in Surrey, England, known for its proximity to Runnymede and its large common land.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed9585e788190bec2d39deba3750f completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefa62d0e081909aaed2978a840734 completed March 9, 2026, 4:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69b54c67eddc819097eff878c860f3d5 completed March 14, 2026, 11:54 a.m.
Created at: March 9, 2026, 3:34 p.m.