Triple

T23214951
Position Surface form Disambiguated ID Type / Status
Subject Heinrich Scholz E580709 entity
Predicate familyName P18 FINISHED
Object Scholz 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: Scholz | Statement: [Heinrich Scholz, familyName, Scholz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Scholz
Context triple: [Heinrich Scholz, familyName, Scholz]
  • A. Scholz chosen
    Scholz is a German surname most prominently associated with Olaf Scholz, the Chancellor of Germany.
  • B. Heuschling
    Heuschling is the original family surname of French silent film actress Catherine Hessling, known for her work with director Jean Renoir.
  • C. Scholz Bangert
    Scholz Bangert is a notable individual associated with the surname Bangert, recognized for achievements that distinguish them among other bearers of the name.
  • D. Eisenhauer
    Eisenhauer is a German-origin surname best known as the ancestral form of the name borne by U.S. President Dwight D. Eisenhower.
  • E. Schlein
    Schlein is the surname of Elly Schlein, an Italian politician and leader of the centre-left Democratic Party.
  • 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_69e2460389408190be74f41d217799a9 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f19163b9b88190a68fa6d08d37bdb7 completed April 29, 2026, 5:04 a.m.
Created at: April 17, 2026, 4:08 p.m.