Triple

T13325398
Position Surface form Disambiguated ID Type / Status
Subject Martinair E317427 entity
Predicate foundedBy P104 FINISHED
Object Martin Schröder E320964 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: Martin Schröder | Statement: [Martinair, foundedBy, Martin Schröder]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Martin Schröder
Context triple: [Martinair, foundedBy, Martin Schröder]
  • A. Martin Schröder chosen
    Martin Schröder is a Dutch aviation entrepreneur best known as the founder of the charter airline Martinair.
  • B. Peter Lohmeyer
    Peter Lohmeyer is a German actor known for his versatile performances in film, television, and theater, often appearing in prominent German productions since the late 1980s.
  • C. Christian Scholz
    Christian Scholz is a German computer scientist and open-source developer known for his contributions to web technologies and social software.
  • D. Olli Dittrich
    Olli Dittrich is a German actor, comedian, and musician best known for his work in television sketch comedy and film.
  • E. Florian Haertel
    Florian Haertel is a German journalist and photographer best known as the former husband of British actress Alex Kingston.
  • 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_69d806b4d62c81908d4ced1665414be5 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d9992c1fec8190bcb6a6bb3c973a24 completed April 11, 2026, 12:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69fcb6419a3c8190bfaeab65f3909474 completed May 7, 2026, 3:56 p.m.
Created at: April 9, 2026, 9:30 p.m.