Triple

T4668160
Position Surface form Disambiguated ID Type / Status
Subject San Francisco Chinatown E102897 entity
Predicate street P959 FINISHED
Object Clay Street E43084 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: Clay Street | Statement: [San Francisco Chinatown, street, Clay Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Clay Street
Context triple: [San Francisco Chinatown, street, Clay Street]
  • A. Clay Street chosen
    Clay Street is a historic thoroughfare running through San Francisco, notably passing through the city's Chinatown district.
  • B. Carpenter Street
    Carpenter Street is a historic Chinatown district in Kuching, Malaysia, known for its traditional shophouses, temples, and vibrant food and cultural scene.
  • C. Church Street
    Church Street is a major thoroughfare in Pretoria, South Africa, historically significant as one of the city’s central and longest streets.
  • D. Church Street
    Church Street is a central thoroughfare in Sheffield, England, known for housing the historic Sheffield Cathedral and other key city-centre buildings.
  • E. Church Street
    Church Street is a major north–south thoroughfare in Lower Manhattan, New York City, running through the Financial District and passing notable landmarks such as the World Trade Center site.
  • 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_69bd43d9cba4819086c1ab1c2d9d2133 completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd633ec8b08190bf8ffd4c3b946f61 completed March 20, 2026, 3:09 p.m.
NED1 Entity disambiguation (via context triple) batch_69cfeaaf9ea0819091bd0981068e5a72 completed April 3, 2026, 4:28 p.m.
Created at: March 20, 2026, 1:15 p.m.