Triple

T20721187
Position Surface form Disambiguated ID Type / Status
Subject Memel Castle E509315 entity
Predicate hasGermanName P1435 FINISHED
Object Memelburg 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: Memelburg | Statement: [Memel Castle, hasGermanName, Memelburg]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Memelburg
Context triple: [Memel Castle, hasGermanName, Memelburg]
  • A. Memelburg chosen
    Memelburg was the medieval German name for the fortress that later became known as Klaipėda Castle in present-day Lithuania.
  • B. Muntendam
    Muntendam is a village in the Dutch province of Groningen, now administratively part of the municipality of Midden-Groningen.
  • C. Hampoort
    Hampoort is a historic city gate, likely part of the old fortifications of a European town or city.
  • D. Kropswolde
    Kropswolde is a village in the Dutch province of Groningen, known for its rural character and proximity to the Zuidlaardermeer lake.
  • E. Ubbergen
    Ubbergen is a village in the Dutch province of Gelderland, known for its scenic, hilly landscape near Nijmegen and the German border.
  • 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_69e0b4c4cc648190b45fda6e2b20af56 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c1d5eec08190832ffba8a90f3076 completed April 21, 2026, 12:16 a.m.
Created at: April 16, 2026, 12:27 p.m.