Triple

T5304347
Position Surface form Disambiguated ID Type / Status
Subject Greek Street E120060 entity
Predicate near P350 FINISHED
Object Soho Square E129762 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 Square | Statement: [Greek Street, near, Soho Square]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soho Square
Context triple: [Greek Street, near, Soho Square]
  • A. Soho Square chosen
    Soho Square is a historic garden square in London’s Soho district, known as a small green oasis surrounded by offices, restaurants, and media businesses.
  • B. Hanover Square
    Hanover Square is a historic public park and gathering space located in the coastal city of Brunswick, Georgia.
  • C. Hanover Square
    Hanover Square is a historic garden square in London’s Mayfair district, known for its Georgian architecture and proximity to major shopping and commercial areas.
  • D. Grosvenor Square
    Grosvenor Square is a large, historic garden square in London’s Mayfair district, long associated with aristocratic residences and prominent diplomatic buildings.
  • E. Grosvenor Square
    Grosvenor Square is a public square located in the Chorlton-on-Medlock district of Manchester, 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_69bd44704be88190acdb2ac481b0ff55 completed March 20, 2026, 12:58 p.m.
NER Named-entity recognition batch_69bd851cac9c8190a23d96cf3c2e4847 completed March 20, 2026, 5:34 p.m.
NED1 Entity disambiguation (via context triple) batch_69bf10f77b048190b8d3b39b900008d8 completed March 21, 2026, 9:43 p.m.
Created at: March 20, 2026, 1:53 p.m.