Triple

T3164123
Position Surface form Disambiguated ID Type / Status
Subject Manchester E66169 entity
Predicate twinCity P1072 FINISHED
Object St. Petersburg E916 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: St. Petersburg | Statement: [Manchester, twinCity, St. Petersburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: St. Petersburg
Context triple: [Manchester, twinCity, St. Petersburg]
  • A. St. Petersburg chosen
    St. Petersburg is a major Russian port city on the Baltic Sea, renowned for its imperial architecture, cultural heritage, and role as a historic capital of Russia.
  • B. St. Petersburg, Florida
    St. Petersburg, Florida is a coastal city on Florida’s Gulf Coast known for its sunny climate, beaches, and vibrant arts and cultural scene.
  • C. Port of St. Petersburg
    The Port of St. Petersburg is a small municipal marina and recreational port on Florida’s Gulf Coast that primarily serves private vessels, research ships, and local tourism rather than large commercial shipping.
  • D. Pushkino
    Pushkino is a town in Russia that serves as a suburban residential and industrial center northeast of Moscow.
  • E. Samara
    Samara is a design-focused housing and urban innovation company co-founded by Airbnb’s Joe Gebbia to explore new forms of living and community.
  • 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_69ad85850c1481908a9e9c6242238de2 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada61ba98881909106951c8ceeb959 completed March 8, 2026, 4:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69b28e4cdd2c8190a4b09e968b9d39be completed March 12, 2026, 9:58 a.m.
Created at: March 8, 2026, 3:06 p.m.