Triple

T15476705
Position Surface form Disambiguated ID Type / Status
Subject Mandarin Oriental Hyde Park, London E376797 entity
Predicate location P40 FINISHED
Object Knightsbridge E77845 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: Knightsbridge | Statement: [Mandarin Oriental Hyde Park, London, location, Knightsbridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Knightsbridge
Context triple: [Mandarin Oriental Hyde Park, London, location, Knightsbridge]
  • A. Knightsbridge chosen
    Knightsbridge is an affluent central London district renowned for its luxury shopping, upscale residences, and proximity to Hyde Park.
  • B. Sloane Square
    Sloane Square is a prominent public square and transport hub in central London, known for its upscale shops, theatres, and proximity to the fashionable Chelsea district.
  • C. Mayfair
    Mayfair is a residential neighborhood located within the city of Homewood, Alabama.
  • D. Mayfair
    Mayfair is an affluent central London district known for its luxury shops, exclusive residences, and prestigious hotels and restaurants.
  • E. St John’s Wood
    St John’s Wood is an affluent residential district in northwest London, known for its tree-lined streets, elegant villas, and landmarks such as Lord’s Cricket Ground and Abbey Road.
  • 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_69d85cd21dcc81908646251b1c26ea00 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e03f88a5dc8190a2d7830748e29180 completed April 16, 2026, 1:46 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff3d4448c08190ac640642cc8fc41f completed May 9, 2026, 1:57 p.m.
Created at: April 10, 2026, 3:34 a.m.