Triple

T3774726
Position Surface form Disambiguated ID Type / Status
Subject County of Mark E83280 entity
Predicate hasCastle P22469 FINISHED
Object Burg Mark E387259 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: Burg Mark | Statement: [County of Mark, hasCastle, Burg Mark]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Burg Mark
Context triple: [County of Mark, hasCastle, Burg Mark]
  • A. Burg Mark chosen
    Burg Mark is a historic medieval castle in the former County of Mark in present-day Germany, which served as the political and administrative center of the region.
  • B. Wechselburg
    Wechselburg is a small municipality in Saxony, Germany, known for its historic Benedictine monastery and scenic location along the Zwickauer Mulde river.
  • C. Verwoerdburg
    Verwoerdburg was the former name of part of the modern South African city of Centurion, historically associated with the apartheid-era figure Hendrik Verwoerd.
  • D. Reideburg
    Reideburg is a district of Halle (Saale) in the German state of Saxony-Anhalt, known as the birthplace of prominent politician Hans-Dietrich Genscher.
  • E. Valkhof
    Valkhof is a historic site in Nijmegen, Netherlands, known for its hilltop park and medieval castle ruins overlooking the River Waal.
  • 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_69ad8b235e608190b5a2b1d1bfcef50b completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcc594c50819099ab5ac1b82f61a6 completed March 8, 2026, 7:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb1616008190a6ec9a2df5bac2b4 completed March 14, 2026, 6:07 a.m.
Created at: March 8, 2026, 3:36 p.m.