Triple

T19707176
Position Surface form Disambiguated ID Type / Status
Subject 999 California Street E473247 entity
Predicate hasViewOf P854 FINISHED
Object Bay Bridge NE NERFINISHED

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: Bay Bridge | Statement: [999 California Street, hasViewOf, Bay Bridge]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bay Bridge
Context triple: [999 California Street, hasViewOf, Bay Bridge]
  • A. Bay Bridge
    Bay Bridge is a prominent cable-stayed highway bridge in Yokohama, Japan, spanning Tokyo Bay and serving as a key part of the city's waterfront skyline.
  • B. Bay Bridge chosen
    The Bay Bridge is a major suspension bridge complex in the San Francisco Bay Area that connects San Francisco and Oakland across San Francisco Bay.
  • C. Jones Bridge
    Jones Bridge is a historic neoclassical bridge in Manila, Philippines, known for connecting key districts across the Pasig River and serving as an iconic city landmark.
  • D. Gateway Bridge
    Gateway Bridge is a major toll bridge in Brisbane, Australia, carrying traffic across the Brisbane River as part of the city’s key motorway network.
  • E. Mount Hope Bridge
    Mount Hope Bridge is a historic suspension bridge in Rhode Island that spans Mount Hope Bay, carrying traffic between Bristol and Aquidneck Island.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e516dd048190a0b6c93ea3e71f58 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e642bb5cd4819090e4c62bd74c4324 completed April 20, 2026, 3:14 p.m.
Created at: April 10, 2026, 1:46 p.m.