Triple

T6510927
Position Surface form Disambiguated ID Type / Status
Subject Ernst May E150130 entity
Predicate name P16 FINISHED
Object Ernst May E150130 NE FINISHED

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: Ernst May | Statement: [Ernst May, name, Ernst May]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ernst May
Context triple: [Ernst May, name, Ernst May]
  • A. Ernst May chosen
    Ernst May was a pioneering German modernist architect and urban planner best known for his large-scale social housing projects in Frankfurt during the 1920s.
  • B. Ernst Göhner
    Ernst Göhner was a prominent Swiss entrepreneur and industrialist known for building a major construction and real estate empire and for his significant philanthropic legacy.
  • C. Fritz Jaenecke
    Fritz Jaenecke was a German architect best known for designing major sports venues, including the Ullevi Stadium in Gothenburg, Sweden.
  • D. Otto Josten
    Otto Josten was the founder of Jostens, the American company best known for producing class rings, yearbooks, and other school-related memorabilia.
  • E. Ernst Wollweber
    Ernst Wollweber was a German communist politician and former head of East Germany’s Ministry for State Security (Stasi) known for his role in building the early East German security apparatus.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69c687ef291081909d437f035eef1cda completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c69f3ad7d081909162f1a625fc52b1 completed March 27, 2026, 3:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69e343941ae481909489cf7a4abdba68 completed April 18, 2026, 8:40 a.m.
Created at: March 27, 2026, 1:43 p.m.