Triple

T7775717
Position Surface form Disambiguated ID Type / Status
Subject Thea von Harbou E221384 entity
Predicate familyName P18 FINISHED
Object von Harbou E221384 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: von Harbou | Statement: [Thea von Harbou, familyName, von Harbou]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: von Harbou
Context triple: [Thea von Harbou, familyName, von Harbou]
  • A. Thea von Harbou chosen
    Thea von Harbou was a German screenwriter, novelist, and filmmaker best known for writing the novel and co-authoring the screenplay for the classic science fiction film "Metropolis."
  • B. F. W. Murnau
    F. W. Murnau was a pioneering German film director of the silent era, best known for expressionist and visually innovative classics such as "Nosferatu" and "Sunrise."
  • C. Fritz Lang
    Fritz Lang was an influential Austrian-German filmmaker and screenwriter, best known for pioneering expressionist cinema with classics like "Metropolis" and "M."
  • D. Walter Rohland
    Walter Rohland was a German industrialist and steel executive who played a significant role in managing armaments production for Nazi Germany during World War II.
  • E. Gustaf Ising
    Gustaf Ising was a Swedish physicist known for early work on particle acceleration and for supervising Nobel laureate Hannes Alfvén’s doctoral research.
  • 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_69ca83ebbef881909ac47f789145fef7 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69caa4d005808190ac14c8d716421bdb completed March 30, 2026, 4:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69ccbd5d671481908ecbdb8ce6ef898a completed April 1, 2026, 6:38 a.m.
Created at: March 30, 2026, 3:51 p.m.