Triple

T20854103
Position Surface form Disambiguated ID Type / Status
Subject Hanns Sachs E513434 entity
Predicate givenName P17 FINISHED
Object Hanns 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: Hanns | Statement: [Hanns Sachs, givenName, Hanns]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hanns
Context triple: [Hanns Sachs, givenName, Hanns]
  • A. Hanns Sachs chosen
    Hanns Sachs was an Austrian psychoanalyst and close early follower of Sigmund Freud, known for his contributions to psychoanalytic theory and practice.
  • B. W. Franz
    W. Franz was a physicist and academic known for supervising the doctoral work of future Nobel laureate Peter Grünberg.
  • C. Hans Müller-Einigen
    Hans Müller-Einigen was an Austrian writer and dramatist best known for his work as an opera librettist in the early 20th century.
  • D. Hanns Lothar
    Hanns Lothar was a German film and stage actor known for his character roles in postwar cinema and for appearing in international productions such as Billy Wilder’s comedy "One, Two, Three."
  • E. Hans-Jürgen
    Hans-Jürgen is a masculine German given name, typically used as a compound first name combining "Hans" and "Jürgen."
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a6015081909f604a88d04b36ea completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.