Triple

T10820090
Position Surface form Disambiguated ID Type / Status
Subject San Francisco E255343 entity
Predicate hasLandmark P105 FINISHED
Object Painted Ladies E2796 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: Painted Ladies | Statement: [San Francisco, hasLandmark, Painted Ladies]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Painted Ladies
Context triple: [San Francisco, hasLandmark, Painted Ladies]
  • A. Painted Ladies chosen
    Painted Ladies are a famous row of colorful Victorian and Edwardian houses in San Francisco, often photographed with the city skyline in the background.
  • B. The Grand Old Lady
    The Grand Old Lady was the affectionate nickname of HMS Warspite, a famed British Royal Navy battleship renowned for her long and distinguished combat service in both World Wars.
  • C. Picket Fences
    Picket Fences is an American television drama series from the 1990s that explores complex social and moral issues in a small-town setting.
  • D. Riverhouse
    Riverhouse is a luxury eco-friendly residential condominium building located in Manhattan’s Battery Park City neighborhood.
  • E. Moon River Estates
    Moon River Estates is a small residential community located within the Municipal District of Willow Creek No. 26 in southern Alberta, Canada.
  • 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_69d73449eee88190afa52c4e6ef96baa completed April 9, 2026, 5:08 a.m.
NED1 Entity disambiguation (via context triple) batch_69de8569178481909474e939a3e4c217 completed April 14, 2026, 6:20 p.m.
Created at: April 8, 2026, 9:18 p.m.