Triple

T18611118
Position Surface form Disambiguated ID Type / Status
Subject Third Street (San Francisco) E454895 entity
Predicate connects P390 FINISHED
Object SoMa 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: SoMa | Statement: [Third Street (San Francisco), connects, SoMa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: SoMa
Context triple: [Third Street (San Francisco), connects, SoMa]
  • A. SoMa chosen
    SoMa is a large, formerly industrial neighborhood in San Francisco known for its tech offices, lofts, nightlife, and cultural institutions.
  • B. NEON District
    NEON District is a vibrant urban arts and entertainment neighborhood known for its creative culture, public art, and role as a hub for festivals and community events.
  • C. Mosaic District
    Mosaic District is a mixed-use urban neighborhood and shopping destination in Merrifield, Virginia, known for its upscale retail, dining, entertainment, and walkable, community-focused design.
  • D. Opportunity District
    Opportunity District is one of the three main themed zones at Expo 2020 Dubai, focused on social impact, unlocking human potential, and sustainable development initiatives.
  • E. Mobility District
    Mobility District is one of Expo 2020 Dubai’s main themed zones, dedicated to showcasing innovations and ideas around movement, transportation, and the seamless flow of people, goods, and information.
  • 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_69d8d38bbe7c8190bdec3138e7d413c9 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e54d013748819099126e27e7ec543d completed April 19, 2026, 9:45 p.m.
Created at: April 10, 2026, 11:45 a.m.