Triple

T4642445
Position Surface form Disambiguated ID Type / Status
Subject Bunker Hill E101683 entity
Predicate hasStreet P959 FINISHED
Object 1st Street E378786 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: 1st Street | Statement: [Bunker Hill, hasStreet, 1st Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: 1st Street
Context triple: [Bunker Hill, hasStreet, 1st Street]
  • A. 1st Street chosen
    1st Street is a major east–west thoroughfare in Los Angeles that runs through neighborhoods including Little Tokyo and connects key parts of the city’s downtown area.
  • B. 1st Avenue
    1st Avenue is a major north–south thoroughfare in downtown Seattle, Washington, known for running through historic and waterfront districts.
  • C. 2nd Street
    2nd Street is a major east–west thoroughfare in downtown Los Angeles that runs through the historic Little Tokyo neighborhood and connects several key districts in the city.
  • D. North First Avenue
    North First Avenue is a street in Barstow, California, known for hosting historic landmarks such as the Harvey House Railroad Depot.
  • E. First Street
    First Street is a modern mixed-use district in central Manchester, England, known for its cultural venues, offices, dining, and public spaces.
  • 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_69bd43d3bc7c81908f81fcf380476b0f completed March 20, 2026, 12:55 p.m.
NER Named-entity recognition batch_69bd5a93047c8190990c94fd5a57c867 completed March 20, 2026, 2:32 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdfad80f14819097e022c9d9da17eb completed March 21, 2026, 1:56 a.m.
Created at: March 20, 2026, 1:14 p.m.