Triple

T17594477
Position Surface form Disambiguated ID Type / Status
Subject Robert the Wise E428531 entity
Predicate mother P120 FINISHED
Object Mary of Hungary 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: Mary of Hungary | Statement: [Robert the Wise, mother, Mary of Hungary]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary of Hungary
Context triple: [Robert the Wise, mother, Mary of Hungary]
  • A. Mary of Hungary
    Mary of Hungary was a 16th-century Habsburg archduchess who served as Queen of Hungary and later as the influential governor of the Habsburg Netherlands.
  • B. Mary of Hungary chosen
    Mary of Hungary was a 13th-century Hungarian princess, daughter of King Stephen V, who became a nun and later an abbess known for her piety and charitable works.
  • C. Catherine of Hungary
    Catherine of Hungary was a medieval Hungarian princess from the House of Anjou, known primarily as a royal daughter whose early death left little political impact.
  • D. Catherine of Hungary
    Catherine of Hungary was a 13th-century Hungarian princess of the Árpád dynasty, known primarily as a daughter of King Béla IV of Hungary.
  • E. Elisabeth of Hungary
    Elisabeth of Hungary was a 13th-century Hungarian princess renowned for her charitable works and deep piety, later canonized as a Catholic saint.
  • 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_69d889e1030481909950e140c63255b9 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e469ea1ac8819083b8449ccdaf2445 completed April 19, 2026, 5:36 a.m.
Created at: April 10, 2026, 5:51 a.m.