Triple

T2649816
Position Surface form Disambiguated ID Type / Status
Subject Rusholme E53869 entity
Predicate adjacentTo P224 FINISHED
Object Longsight E184455 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: Longsight | Statement: [Rusholme, adjacentTo, Longsight]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Longsight
Context triple: [Rusholme, adjacentTo, Longsight]
  • A. Longsight chosen
    Longsight is a residential district in Manchester, England, known for its diverse community, busy market, and proximity to the city centre.
  • B. Cloudesley
    Cloudesley is a lesser-known 1830 novel by William Godwin that explores themes of inheritance, identity, and moral responsibility within a Gothic-influenced narrative.
  • C. Ramsden
    Ramsden is a small rural village in the West Oxfordshire district of England, known for its traditional Cotswold character and surrounding countryside.
  • D. Winston Lights
    Winston Lights is a lighter-tar, lower-nicotine variant of the Winston brand of cigarettes marketed as a milder smoking option.
  • E. Sightlines
    Sightlines is a major contemporary art project by Canadian painter Wanda Koop that explores themes of perception, landscape, and the impact of technology on how we see the world.
  • 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_69ab495e192081909c77b622e8e7e15a completed March 6, 2026, 9:38 p.m.
NER Named-entity recognition batch_69abd91ca1288190ba302b04bac4c153 completed March 7, 2026, 7:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69af98cc2d9881908556b915a1870c02 completed March 10, 2026, 4:06 a.m.
Created at: March 6, 2026, 9:53 p.m.