Triple

T4835684
Position Surface form Disambiguated ID Type / Status
Subject Thames House E108052 entity
Predicate locatedOn P40 FINISHED
Object Millbank E375747 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: Millbank | Statement: [Thames House, locatedOn, Millbank]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Millbank
Context triple: [Thames House, locatedOn, Millbank]
  • A. Millbank chosen
    Millbank is a riverside area in central London known for its government buildings, art institutions like Tate Britain, and proximity to the Houses of Parliament.
  • B. Wellbank
    Wellbank is a small rural village in the Angus council area of eastern Scotland.
  • C. Mill Hill
    Mill Hill is a suburban area in the London Borough of Barnet, known for its residential character, green spaces, and local schools.
  • D. Mills Hill
    Mills Hill is a railway station in Greater Manchester, England, serving the local communities of Middleton and Chadderton.
  • E. Pound Hill
    Pound Hill is a residential neighbourhood and one of the main suburban areas within the town of Crawley in West Sussex, England.
  • 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_69bd43fbe444819085cb970706ef73f7 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6ce00cd48190a675fb75eae152c2 completed March 20, 2026, 3:50 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4dda71e08190a28215f91405a4e1 completed March 21, 2026, 7:50 a.m.
Created at: March 20, 2026, 1:25 p.m.