Triple

T18195428
Position Surface form Disambiguated ID Type / Status
Subject Hermann Billung E435648 entity
Predicate spouse P13 FINISHED
Object Oda 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: Oda | Statement: [Hermann Billung, spouse, Oda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oda
Context triple: [Hermann Billung, spouse, Oda]
  • A. Oda chosen
    Oda was a medieval noblewoman best known as the mother of Bernard I, Duke of Saxony, and a member of the influential Saxon aristocracy.
  • B. Oda
    Oda is a town located in the Eastern Region of Ghana, known for its role as a local commercial and administrative center.
  • C. Oda
    Oda is a Japanese samurai clan most famously associated with the powerful 16th-century warlord Oda Nobunaga, a key figure in the unification of Japan.
  • D. Oda Jaune
    Oda Jaune is a Bulgarian-born contemporary painter known for her surreal, often unsettling figurative works and her association with the German art scene.
  • E. Odo-Ya
    "Odo-Ya" is a song featured on the soundtrack album for Disney's animated film "Encanto."
  • 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_69d8b90dba6481908e119eb9aa4ca0cb completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e4e0d2ad5881909d846f3851ac9ec9 completed April 19, 2026, 2:04 p.m.
Created at: April 10, 2026, 10:31 a.m.