Triple

T19367490
Position Surface form Disambiguated ID Type / Status
Subject St Mary le Strand E484439 entity
Predicate locatedNear P294 FINISHED
Object Somerset House 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: Somerset House | Statement: [St Mary le Strand, locatedNear, Somerset House]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Somerset House
Context triple: [St Mary le Strand, locatedNear, Somerset House]
  • A. Somerset House, London chosen
    Somerset House in London is a grand 18th-century riverside complex renowned for its neoclassical design and its role as a major cultural and arts centre.
  • B. Wellington House, London
    Wellington House in London is a government office building that serves as the central administrative base for Public Health England.
  • C. Burlington House
    Burlington House is a historic building complex on London's Piccadilly that houses several learned societies and the Royal Academy of Arts.
  • D. Kemp House
    Kemp House is a historic early 19th-century wooden mission house in Kerikeri, New Zealand, and one of the country’s oldest surviving European buildings.
  • E. Portcullis House
    Portcullis House is a modern parliamentary office building in Westminster that provides workspaces for members of the UK House of Commons and their staff.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619adac8881909136c50351f3683d completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.