Triple

T19371005
Position Surface form Disambiguated ID Type / Status
Subject Port of Ventspils E484534 entity
Predicate region P40 FINISHED
Object Kurzeme 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: Kurzeme | Statement: [Port of Ventspils, region, Kurzeme]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kurzeme
Context triple: [Port of Ventspils, region, Kurzeme]
  • A. Kurzeme chosen
    Kurzeme is a historical and cultural region in western Latvia, known for its Baltic Sea coastline, forests, and traditional Latvian heritage.
  • B. Vidzeme
    Vidzeme is a historical region in northern Latvia known for its rich cultural heritage, forests, and role in the development of Latvian national identity.
  • C. Kosere
    "Kosere" is a popular Nigerian song by singer CDQ, known for its energetic Afrobeat style and street-influenced lyrics.
  • D. Kuršumlija
    Kuršumlija is a small town and municipality in southern Serbia, known for its nearby monasteries and location at the confluence of the Toplica and Kosanica rivers.
  • E. Kūruš
    Kūruš is the Old Persian form of the name Cyrus, borne by early Achaemenid kings of ancient Persia.
  • 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_69d8e8d305088190ad13571532aa454c completed April 10, 2026, 12:10 p.m.
NER Named-entity recognition batch_69e619b09ef08190a8b420316c0b8eb3 completed April 20, 2026, 12:18 p.m.
Created at: April 10, 2026, 1:35 p.m.