Triple

T16698787
Position Surface form Disambiguated ID Type / Status
Subject Japantown, San Francisco E405786 entity
Predicate developedAsJapantownBy P5216 FINISHED
Object Japanese immigrants LITERAL 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: Japanese immigrants | Statement: [Japantown, San Francisco, developedAsJapantownBy, Japanese immigrants]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: developedAsJapantownBy
Context triple: [Japantown, San Francisco, developedAsJapantownBy, Japanese immigrants]
  • A. developedAs chosen
    Indicates that one entity was created, designed, or evolved specifically to function as or replace another entity.
  • B. developedAlong
    Indicates that something was created, constructed, or evolved following the course, path, or boundary of something else.
  • C. wasDevelopedIn
    Indicates that an entity (such as a product, technology, or work) came into existence or was created during a specific time period or at a particular place.
  • D. placeOfDevelopment
    Indicates the location where something (such as a product, project, or work) was created, designed, or developed.
  • E. developedAsNewTown
    Indicates that a settlement or urban area was intentionally planned and constructed as a new town, rather than evolving organically from an existing settlement.
  • F. None of above.

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_69d8838db21081909589220fd71440a4 completed April 10, 2026, 4:58 a.m.
NER Named-entity recognition batch_69e3832f550c8190bf7514d4611dec6a completed April 18, 2026, 1:12 p.m.
PD Predicate disambiguation batch_69e319bc73908190a0e38bc926b31f10 completed April 18, 2026, 5:42 a.m.
Created at: April 10, 2026, 5:19 a.m.