Triple

T4996853
Position Surface form Disambiguated ID Type / Status
Subject Ventspils E112267 entity
Predicate hasLandmark P105 FINISHED
Object Ventspils Old Town E112267 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: Ventspils Old Town | Statement: [Ventspils, hasLandmark, Ventspils Old Town]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ventspils Old Town
Context triple: [Ventspils, hasLandmark, Ventspils Old Town]
  • A. Ventspils chosen
    Ventspils is a port city on Latvia’s Baltic Sea coast known for its major ice-free harbor, oil and cargo terminals, and well-preserved historic center.
  • B. Bauska
    Bauska is a historic town in southern Latvia known for its medieval castle and location at the confluence of the Mūsa and Mēmele rivers, which form the Lielupe.
  • C. Kuldīga
    Kuldīga is a historic town in western Latvia known for its well-preserved old town and proximity to the Venta Rapid, one of Europe’s widest natural waterfalls.
  • D. Kaunas Old Town
    Kaunas Old Town is the historic center of Kaunas, Lithuania, known for its medieval architecture, cobblestone streets, and well-preserved cultural landmarks.
  • E. Riga Castle
    Riga Castle is a historic fortress on the banks of the Daugava River in Latvia’s capital, serving as both a symbol of the city’s past and the official residence of the country’s president.
  • 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_69bd4432b32c81909f3b3c6bd10f0653 completed March 20, 2026, 12:57 p.m.
NER Named-entity recognition batch_69bd72a130708190b9bc1393ba78bfb1 completed March 20, 2026, 4:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69be8a3489f08190a338de8d8be09813 completed March 21, 2026, 12:08 p.m.
Created at: March 20, 2026, 1:34 p.m.