Triple

T10829712
Position Surface form Disambiguated ID Type / Status
Subject W1 postcode district E255584 entity
Predicate containsLandmark P1098 FINISHED
Object Portland Place E378431 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: Portland Place | Statement: [W1 postcode district, containsLandmark, Portland Place]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Portland Place
Context triple: [W1 postcode district, containsLandmark, Portland Place]
  • A. Portland Place chosen
    Portland Place is a major street in central London known for its Georgian architecture and prominent institutions, including the BBC's Broadcasting House.
  • B. Portman Street
    Portman Street is a central London street in the City of Westminster, known for connecting the Marylebone area to the busy Oxford Street shopping district.
  • C. Blackett Street
    Blackett Street is a central thoroughfare in Newcastle upon Tyne, England, known for its shops, bus routes, and proximity to key city landmarks.
  • D. Eastgate Street
    Eastgate Street is one of the main historic shopping and thoroughfare streets in the centre of Gloucester, England.
  • E. Curzon Street
    Curzon Street is a prestigious street in London’s Mayfair district, known for its historic architecture, embassies, and exclusive residences.
  • 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_69d6aa8081448190a9324184f2bd1c26 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d74420fa188190b5b3c59e1a9f551d completed April 9, 2026, 6:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69de85a068b08190948c3ca32cdda147 completed April 14, 2026, 6:21 p.m.
Created at: April 8, 2026, 9:19 p.m.