Triple

T19523768
Position Surface form Disambiguated ID Type / Status
Subject Melngalvju nams E488467 entity
Predicate locatedOn P40 FINISHED
Object Rātslaukums 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: Rātslaukums | Statement: [Melngalvju nams, locatedOn, Rātslaukums]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rātslaukums
Context triple: [Melngalvju nams, locatedOn, Rātslaukums]
  • A. Rātslaukums chosen
    Rātslaukums is the historic Town Hall Square in Riga, Latvia, known for its reconstructed medieval buildings such as the House of the Blackheads.
  • B. Lauvsnes
    Lauvsnes is a small coastal village in Trøndelag county, Norway, known as the main local hub of the Flatanger municipality.
  • C. Pamūšis
    Pamūšis is a small settlement in present-day Lithuania, historically notable as the birthplace of Russian field marshal Mikhail Barclay de Tolly.
  • D. Ruklys
    Ruklys was a son of King Mindaugas of Lithuania, known primarily from medieval historical records of the Lithuanian royal family.
  • E. Pardais
    Pardais is a civil parish in the municipality of Vila Viçosa, in Portugal’s Alentejo region.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e636392444819094f6a2aa1cdf3d42 completed April 20, 2026, 2:20 p.m.
Created at: April 10, 2026, 1:41 p.m.