Triple

T20599891
Position Surface form Disambiguated ID Type / Status
Subject Superman E506145 entity
Predicate producer P490 FINISHED
Object Pierre Spengler 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: Pierre Spengler | Statement: [Superman, producer, Pierre Spengler]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pierre Spengler
Context triple: [Superman, producer, Pierre Spengler]
  • A. Pierre Spengler chosen
    Pierre Spengler is a film producer best known for his work on the original Superman film series.
  • B. Erich Kähler
    Erich Kähler was a German mathematician known for his foundational work in differential geometry and complex manifolds, particularly the introduction of Kähler geometry.
  • C. Fritz Trautwein
    Fritz Trautwein was a German architect best known for designing Hamburg’s iconic Heinrich-Hertz Tower telecommunications structure.
  • D. Max von Forckenbeck
    Max von Forckenbeck was a prominent 19th-century German liberal politician who served as mayor of both Berlin and Breslau and played a leading role in the development of parliamentary democracy in Prussia and the German Empire.
  • E. Hermann von Boyen
    Hermann von Boyen was a Prussian general and statesman who played a key role in modernizing the Prussian army in the early 19th century.
  • 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_69e0b4ba6ae88190af871e1f9522c704 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6aa1ef9ac8190b05e23c149529cb9 completed April 20, 2026, 10:35 p.m.
Created at: April 16, 2026, 11:40 a.m.