Triple

T469596
Position Surface form Disambiguated ID Type / Status
Subject Martin Luther E8525 entity
Predicate parent P120 FINISHED
Object Margarethe Luther E59463 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: Margarethe Luther | Statement: [Martin Luther, parent, Margarethe Luther]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Margarethe Luther
Context triple: [Martin Luther, parent, Margarethe Luther]
  • A. Katharina von Bora
    Katharina von Bora was a former nun who became the wife of Protestant Reformer Martin Luther and played a key role in managing his household and supporting the early Lutheran movement.
  • B. Elisabeth Luther chosen
    Elisabeth Luther was one of the daughters of the German Reformation leader Martin Luther and his wife Katharina von Bora, who died in early childhood.
  • C. Anna von Bönninghausen
    Anna von Bönninghausen was a 17th-century German noblewoman best known as the mother of Bernhard von Galen, the influential Prince-Bishop of Münster.
  • D. Maria Barbara Bach
    Maria Barbara Bach was a German singer and the first wife of composer Johann Sebastian Bach, with whom she had several musically gifted children.
  • E. Hans Luther
    Hans Luther was the father of Protestant Reformer Martin Luther, a German miner and smelter who rose to become a relatively prosperous businessman in early 16th-century Saxony.
  • 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_69a2e7f3aeb48190a19453e3a043f486 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2efee0ea0819099d87f3727c03bc7 completed Feb. 28, 2026, 1:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4777ac3748190989ab6a9565d2c8a completed March 1, 2026, 5:29 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.