Triple

T3750836
Position Surface form Disambiguated ID Type / Status
Subject Kaliningrad Oblast E81323 entity
Predicate hasPortCity P2745 FINISHED
Object Baltiysk E186943 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: Baltiysk | Statement: [Kaliningrad Oblast, hasPortCity, Baltiysk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Baltiysk
Context triple: [Kaliningrad Oblast, hasPortCity, Baltiysk]
  • A. Baltiysk chosen
    Baltiysk is a Russian port town in the Kaliningrad Oblast, strategically located on the Baltic Sea and serving as an important naval base.
  • B. Baltica
    Baltica is an ancient Precambrian continental craton that now underlies much of northern and eastern Europe, including parts of Scandinavia and western Russia.
  • C. Baltus
    Baltus is a fictional character best known as the wealthy farmer and father of Katrina Van Tassel in Washington Irving’s short story “The Legend of Sleepy Hollow.”
  • D. Aukštaitija
    Aukštaitija is a historical and ethnographic region in northeastern Lithuania known for its lakes, forests, and strong preservation of traditional Lithuanian culture and dialects.
  • E. Sudetes
    The Sudetes are a mountain range in Central Europe spanning parts of Poland, the Czech Republic, and Germany, known for their forested peaks, mineral resources, and popular spa and ski resorts.
  • 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_69ad8b19b7b08190a6188804e99c53e9 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcb909bb4819088559f90d718f72f completed March 8, 2026, 7:18 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4db34aa5c8190ba3f22ee0f1f4208 completed March 14, 2026, 3:51 a.m.
Created at: March 8, 2026, 3:35 p.m.