Triple

T12940270
Position Surface form Disambiguated ID Type / Status
Subject Kelly’s Steps E309617 entity
Predicate connectsTo P845 FINISHED
Object Salamanca Place E115134 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: Salamanca Place | Statement: [Kelly’s Steps, connectsTo, Salamanca Place]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salamanca Place
Context triple: [Kelly’s Steps, connectsTo, Salamanca Place]
  • A. Salamanca Place chosen
    Salamanca Place is a historic waterfront precinct in Hobart, Tasmania, renowned for its preserved sandstone warehouses, vibrant markets, and cultural venues.
  • B. La Ronda Street
    La Ronda Street is a famous colonial-era lane in Quito known for its preserved architecture, traditional artisan workshops, and vibrant nightlife.
  • C. Park Place
    Park Place is a street in Lower Manhattan, New York City, known for its proximity to major subway stations and the World Trade Center area.
  • D. Valencia Street
    Valencia Street is a major commercial and cultural corridor in San Francisco’s Mission District, known for its vibrant mix of restaurants, bars, boutiques, and arts venues.
  • E. Balcarce Street
    Balcarce Street is a historic street in Buenos Aires, Argentina, known for running alongside key government buildings and landmarks in the city’s central district.
  • 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_69d7bdfa933c8190b5a27aa4a08a19b7 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d97dca2ee88190b45fafe7d53c35c9 completed April 10, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af70f45c8190a40250da4a787d8f completed May 3, 2026, 2:14 a.m.
Created at: April 9, 2026, 5:43 p.m.