Triple

T3374627
Position Surface form Disambiguated ID Type / Status
Subject Tilda Swinton E71037 entity
Predicate familyName P18 FINISHED
Object Swinton E328131 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: Swinton | Statement: [Tilda Swinton, familyName, Swinton]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Swinton
Context triple: [Tilda Swinton, familyName, Swinton]
  • A. Swinton
    Swinton is a town in the City of Salford, Greater Manchester, England, known historically for its role in the coal mining and textile industries.
  • B. Swinton chosen
    Swinton is a small rural village in the historic county of Berwickshire in the Scottish Borders region of Scotland.
  • C. Hillman
    Hillman is a residential suburb in the City of Rockingham within the Perth metropolitan region of Western Australia.
  • D. Sunbeam
    Sunbeam is a well-known consumer brand specializing in household appliances and home comfort products, owned by Newell Brands.
  • E. Morris
    Morris is a common English-language surname borne by numerous notable figures in politics, arts, sports, and other fields.
  • 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_69ad85a7f80c8190a05e43013f298942 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2bf4ad88190a2c49dc30f323a13 completed March 8, 2026, 5:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69b34bbfaf3081908babba216c7da776 completed March 12, 2026, 11:26 p.m.
Created at: March 8, 2026, 3:13 p.m.