Triple

T24403970
Position Surface form Disambiguated ID Type / Status
Subject Kurskiy Zaliv E615255 entity
Predicate hasOfficialLanguageNameInLithuania P64982 FINISHED
Object Kuršių marios
Kuršių marios is a shallow, brackish lagoon on the Baltic Sea coast, separated from the sea by the Curonian Spit and shared by Lithuania and Russia’s Kaliningrad region.
 E1631038 NE FINISHED

How this triple was built (3 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: Kuršių marios | Statement: [Kurskiy Zaliv, hasOfficialLanguageNameInLithuania, Kuršių marios]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Kuršių marios
Triple: [Kurskiy Zaliv, hasOfficialLanguageNameInLithuania, Kuršių marios]
Generated description
Kuršių marios is a shallow, brackish lagoon on the Baltic Sea coast, separated from the sea by the Curonian Spit and shared by Lithuania and Russia’s Kaliningrad region.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: hasOfficialLanguageNameInLithuania
Context triple: [Kurskiy Zaliv, hasOfficialLanguageNameInLithuania, Kuršių marios]
  • A. hasLanguageOfOfficialName
    Indicates that an entity’s official name is expressed in a specified language.
  • B. hasOfficialNameInEsperanto
    Indicates that an entity has an official name expressed in the Esperanto language.
  • C. hasOfficialCountryLanguage
    Indicates that a country recognizes a particular language as one of its official languages for governmental or legal purposes.
  • D. hasOfficialNameInLatin
    Indicates that an entity has an official or formally recognized name expressed in the Latin language.
  • E. nameInLithuanian chosen
    Indicates that one entity is the Lithuanian-language name or label for another entity.
  • F. None of above.

Provenance (6 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_69e2d7e780bc81908049c779e697a7f6 completed April 18, 2026, 1:01 a.m.
NER Named-entity recognition batch_69f294dcf7f4819094d2a3be163a5822 completed April 29, 2026, 11:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0fd689db7c819093b3225fe2efcf6e completed May 22, 2026, 4:07 a.m.
NEDg Description generation batch_6a0fd870ba548190acc06f694170e997 completed May 22, 2026, 4:15 a.m.
NED2 Entity disambiguation (via description) batch_6a0fd8f7c44881909c84a8baac1bcd02 completed May 22, 2026, 4:17 a.m.
PD Predicate disambiguation batch_69f287c4a2b48190b80fb7a3c0e9b018 completed April 29, 2026, 10:35 p.m.
Created at: April 18, 2026, 2:05 a.m.