Triple

T23452125
Position Surface form Disambiguated ID Type / Status
Subject Moritz von Fries E567809 entity
Predicate givenName P17 FINISHED
Object Moritz 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: Moritz | Statement: [Moritz von Fries, givenName, Moritz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Moritz
Context triple: [Moritz von Fries, givenName, Moritz]
  • A. Moritz chosen
    Moritz is a masculine given name of German origin, commonly used in German-speaking countries.
  • B. Philipp Moritz
    Philipp Moritz is a researcher in machine learning and reinforcement learning, known for co-authoring influential work such as the Proximal Policy Optimization (PPO) algorithm.
  • C. Moritz Klaus
    Moritz Klaus is a German actor best known internationally for his role in the 2022 anti-war film "All Quiet on the Western Front."
  • D. Franz
    Franz is the given name of Franz Cardinal König, a prominent 20th-century Austrian Catholic cardinal and influential church leader.
  • E. Franz
    Franz is the male lead in the ballet "Coppélia," a village youth whose infatuation with a mysterious girl leads to comic and romantic entanglements.
  • 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_69e2458b4c888190b1d7998f9862a558 completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a64ded5c8190bd50ac5b9bbb0f5f completed April 29, 2026, 6:33 a.m.
Created at: April 17, 2026, 5:52 p.m.