Triple

T17444834
Position Surface form Disambiguated ID Type / Status
Subject QLine E424753 entity
Predicate terminus P388 FINISHED
Object Congress 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: Congress Street | Statement: [QLine, terminus, Congress Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Congress Street
Context triple: [QLine, terminus, Congress Street]
  • A. Congress Street
    Congress Street is a historic thoroughfare in downtown Savannah, Georgia, known for its proximity to the city’s iconic squares, shops, and restaurants.
  • B. Congress Street chosen
    Congress Street is a roadway that serves as one of the access points to Boston’s State subway station in the downtown area.
  • C. Congress Street
    Congress Street is a major thoroughfare and historic commercial corridor in downtown Portland, Maine, known for its shops, restaurants, and cultural institutions.
  • D. Washington Street
    Washington Street is a main thoroughfare running through Dedham Square, serving as a central route for local traffic, businesses, and community activity.
  • E. Washington Street
    Washington Street is a major historic thoroughfare in downtown Boston, Massachusetts, running through the city’s central civic and commercial districts.
  • 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_69d889db0ba481908402409af3b37917 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e44ffa2d84819086474649eba1065c completed April 19, 2026, 3:46 a.m.
Created at: April 10, 2026, 5:47 a.m.