Triple

T18195404
Position Surface form Disambiguated ID Type / Status
Subject Hermann Billung E435648 entity
Predicate familyName P18 FINISHED
Object Billung 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: Billung | Statement: [Hermann Billung, familyName, Billung]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Billung
Context triple: [Hermann Billung, familyName, Billung]
  • A. Billung chosen
    Billung was a prominent medieval German noble family that held the Duchy of Saxony and played a key role in the politics of the Holy Roman Empire.
  • B. Biltine
    Biltine is a town in eastern Chad that serves as an administrative and regional center in the Wadi Fira area.
  • C. Billiri
    Billiri is a town and administrative center in northeastern Nigeria known for serving as one of the local government areas within Gombe State.
  • D. Bugulma
    Bugulma is a town in the Republic of Tatarstan, Russia, known as an industrial and cultural center in the southeastern part of the region.
  • E. Billinudgel
    Billinudgel is a small rural village in the Northern Rivers region of New South Wales, Australia, known for its historic pub and laid-back country atmosphere.
  • 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.