Triple

T22055048
Position Surface form Disambiguated ID Type / Status
Subject Kuressaare E544984 entity
Predicate formerName P65 FINISHED
Object Kingissepa 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: Kingissepa | Statement: [Kuressaare, formerName, Kingissepa]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kingissepa
Context triple: [Kuressaare, formerName, Kingissepa]
  • A. Kingissepa chosen
    Kingissepa is the former Soviet-era name of the Estonian town now known as Kuressaare, located on Saaremaa Island.
  • B. Stockheim
    Stockheim is a village and local district within the municipality of Kreuzau in North Rhine-Westphalia, Germany.
  • C. Stockheim
    Stockheim is a village and district of the town of Brackenheim in the Heilbronn district of Baden-Württemberg, Germany.
  • D. Karlbo
    Karlbo is a small locality in Sweden best known as the birthplace of Nobel Prize–winning poet Erik Axel Karlfeldt.
  • E. Rimforsa
    Rimforsa is a small locality in Kinda Municipality in Östergötland County, Sweden.
  • 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_69e11e3377c48190890c17407b9527d6 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f1285681848190a0bbe18d504d1f34 completed April 28, 2026, 9:36 p.m.
Created at: April 16, 2026, 8:26 p.m.