Triple

T16872007
Position Surface form Disambiguated ID Type / Status
Subject M Street Bridge E421191 entity
Predicate carried P2774 FINISHED
Object M 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: M Street | Statement: [M Street Bridge, carried, M Street]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: M Street
Context triple: [M Street Bridge, carried, M Street]
  • A. M Street chosen
    M Street is a common street designation in Washington, D.C., used for several major east–west thoroughfares across different quadrants of the city.
  • B. L Street
    L Street is a major thoroughfare in downtown Sacramento, California, known for running past the California State Capitol and connecting key civic and commercial areas of the city.
  • C. Third Street
    Third Street is a popular shopping and dining corridor in Los Angeles’ Beverly Grove neighborhood, known for its trendy boutiques, cafes, and restaurants.
  • D. Third Street
    Third Street is a major thoroughfare in San Francisco that serves as a key corridor for public transit, including the Muni Metro T Third Street light rail line.
  • E. Third Street
    Third Street is a notable roadway in Kingston’s Trench Town neighborhood, recognized as part of the area’s historic and cultural landscape.
  • 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_69d889d470fc8190b4aec199636c0c56 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e3b7f31b448190a21e3e4d1a0d2f73 completed April 18, 2026, 4:57 p.m.
Created at: April 10, 2026, 5:29 a.m.