Triple

T12779622
Position Surface form Disambiguated ID Type / Status
Subject Robert Hartmann E305470 entity
Predicate name P16 FINISHED
Object Robert Hartmann 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: Robert Hartmann | Statement: [Robert Hartmann, name, Robert Hartmann]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robert Hartmann
Context triple: [Robert Hartmann, name, Robert Hartmann]
  • A. Robert Hartmann chosen
    Robert Hartmann is a technology entrepreneur best known as a founder of the semiconductor company Altera.
  • B. Walter Hartmann
    Walter Hartmann was a German Wehrmacht general who held senior command positions, including corps-level leadership, during World War II.
  • C. Daniel Hartmann
    Daniel Hartmann is a German local politician who serves as the mayor of the town of Höxter in North Rhine-Westphalia.
  • D. Rudolf Haag
    Rudolf Haag was a German theoretical physicist renowned for his foundational contributions to quantum field theory, particularly in formulating the algebraic approach and rigorous scattering theory.
  • E. Richard Riemerschmid
    Richard Riemerschmid was a pioneering German architect and designer associated with Jugendstil and early modernism, known for his influential role in uniting art, craft, and industry.
  • 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_69d7bdf2b43c819098ae5aa68e61ea58 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d96e5a5680819095dcd491486d23e7 completed April 10, 2026, 9:40 p.m.
Created at: April 9, 2026, 5:29 p.m.