Triple

T23266397
Position Surface form Disambiguated ID Type / Status
Subject Dearborn Street E588158 entity
Predicate intersects P1018 FINISHED
Object State Street — 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: State Street | Statement: [Dearborn Street, intersects, State Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: State Street
Context triple: [Dearborn Street, intersects, State Street]
  • A. State Street
    State Street is a major thoroughfare in Augusta, Maine, notable for running past the Maine State House and other key government buildings.
  • B. State Street
    State Street is a notable street in New York City's Financial District, running near landmarks such as Bowling Green and the Battery.
  • C. State Street chosen
    State Street is a major north–south thoroughfare in Utah, forming part of U.S. Route 89 and serving as a key commercial and transportation corridor through the Salt Lake Valley.
  • D. State Street
    State Street is a central thoroughfare and commercial corridor in New Haven, Connecticut, known for its mix of shops, restaurants, and proximity to downtown landmarks.
  • E. State Street
    State Street is a major thoroughfare commonly found in many U.S. cities, often serving as a central commercial or transit corridor.
  • 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_69e25d148adc819088efbf42672604e9 completed April 17, 2026, 4:17 p.m.
NER Named-entity recognition batch_69f194cd13b48190a9c282545a34f348 completed April 29, 2026, 5:19 a.m.
Created at: April 17, 2026, 4:37 p.m.