Triple

T6017856
Position Surface form Disambiguated ID Type / Status
Subject Old Compton Street E133989 entity
Predicate district P2709 FINISHED
Object Soho E22316 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: Soho | Statement: [Old Compton Street, district, Soho]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soho
Context triple: [Old Compton Street, district, Soho]
  • A. Soho chosen
    Soho is a vibrant central London district famed for its nightlife, entertainment venues, and diverse cultural scene.
  • B. Westend
    Westend is a prominent and affluent district in Frankfurt am Main, Germany, known for its elegant residential areas and concentration of banks and corporate offices.
  • C. Kensington Market
    Kensington Market is a vibrant, historically multicultural neighborhood in Toronto known for its eclectic shops, diverse food offerings, and bohemian street culture.
  • D. West End
    West End is a largely residential and commercial area in the western portion of Alexandria, Virginia, known for its diverse communities, apartment complexes, and proximity to major transportation routes.
  • E. West End
    West End is London’s renowned theatre district, famous for its high-profile stage productions and vibrant entertainment scene.
  • 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_69c008742a5c8190b9cb9c2787a3d8b3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04f8458588190a78aa32cbdbecfb1 completed March 22, 2026, 8:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69c12510695c8190a8c379c9802a9089 completed March 23, 2026, 11:33 a.m.
Created at: March 22, 2026, 4:07 p.m.