Triple

T15082877
Position Surface form Disambiguated ID Type / Status
Subject Hellboy Universe E360193 entity
Predicate notableCharacter P1481 FINISHED
Object Johann Kraus E346051 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: Johann Kraus | Statement: [Hellboy Universe, notableCharacter, Johann Kraus]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Johann Kraus
Context triple: [Hellboy Universe, notableCharacter, Johann Kraus]
  • A. Johann Kraus chosen
    Johann Kraus is a disembodied ectoplasmic medium and paranormal investigator in the Hellboy universe, known for his work with the Bureau for Paranormal Research and Defense.
  • B. Andrew Ettingshausen
    Andrew Ettingshausen is a former Australian rugby league star best known as a long-serving Cronulla-Sutherland Sharks and New South Wales representative centre and fullback.
  • C. Karl Wien
    Karl Wien was a German mountaineer known for leading early high-altitude expeditions in Central Asia, including the pioneering ascent of Lenin Peak.
  • D. Johann Hülsemann
    Johann Hülsemann was a prominent 17th-century German Lutheran theologian known for his vigorous defense of Lutheran orthodoxy in doctrinal controversies of his time.
  • E. Georg Lilienthal
    Georg Lilienthal was a German historian and author known for his work on the history and development of puzzles, particularly mechanical puzzles.
  • 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_69d85a035aa88190b52a139d3a1b7b6d completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e0027450a48190a84588b6aaf84ebf completed April 15, 2026, 9:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69feb7e188448190b855ace5ab390646 completed May 9, 2026, 4:28 a.m.
Created at: April 10, 2026, 3:03 a.m.