Triple

T21355314
Position Surface form Disambiguated ID Type / Status
Subject Oskar Hergt E526605 entity
Predicate givenName P17 FINISHED
Object Oskar 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: Oskar | Statement: [Oskar Hergt, givenName, Oskar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Oskar
Context triple: [Oskar Hergt, givenName, Oskar]
  • A. Oskar chosen
    Oskar is a masculine given name of Germanic origin, commonly used in various European countries.
  • B. Erich
    Erich is a masculine given name of German origin, commonly used in German-speaking countries and beyond.
  • C. Helmut
    Helmut is a masculine given name of German origin, historically common in German-speaking countries.
  • D. Jacob Heym
    Jacob Heym is the fictional Jewish shopkeeper in a World War II ghetto who becomes a reluctant symbol of hope by spreading invented news in the story "Jacob the Liar."
  • E. Alois
    Alois is a masculine given name of Germanic origin, notably borne by Alois Hitler, the father of Adolf Hitler.
  • 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_69e0b51cd5cc81909ac1187971e8a8ad completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e8af9cd4a48190aa6e72c019b60f8c completed April 22, 2026, 11:23 a.m.
Created at: April 16, 2026, 5:06 p.m.