Triple

T12713464
Position Surface form Disambiguated ID Type / Status
Subject Breakfast Point E303778 entity
Predicate adjacentTo P224 FINISHED
Object Mortlake E309964 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: Mortlake | Statement: [Breakfast Point, adjacentTo, Mortlake]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mortlake
Context triple: [Breakfast Point, adjacentTo, Mortlake]
  • A. Mortlake chosen
    Mortlake is a riverside suburb in Sydney, Australia, known for its location on the Parramatta River and mix of residential and light industrial areas.
  • B. Mortlake
    Mortlake is a riverside district in southwest London on the River Thames, known as the traditional finishing point of the annual Oxford–Cambridge Boat Race.
  • C. Ingliston
    Ingliston is a village and district in western Edinburgh, Scotland, best known for hosting the Royal Highland Centre and being adjacent to Edinburgh Airport.
  • D. Burwood
    Burwood is a suburb in Sydney’s Inner West known for its diverse community, busy commercial centre, and strong transport links to the city.
  • E. Brookvale
    Brookvale is a residential suburb within the town of Runcorn in Cheshire, 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_69d7bdf084148190ab9d513dc0735af4 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9620a7554819083784897ff690652 completed April 10, 2026, 8:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f684e43424819080659ab152caae52 completed May 2, 2026, 11:12 p.m.
Created at: April 9, 2026, 5:23 p.m.