Triple

T7293908
Position Surface form Disambiguated ID Type / Status
Subject Jan van der Does E164466 entity
Predicate alternateName P39 FINISHED
Object Janus Dousa Senior E654664 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: Janus Dousa Senior | Statement: [Jan van der Does, alternateName, Janus Dousa Senior]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janus Dousa Senior
Context triple: [Jan van der Does, alternateName, Janus Dousa Senior]
  • A. Janus Dousa chosen
    Janus Dousa was a 16th-century Dutch statesman, humanist scholar, poet, and the first librarian of Leiden University, known for his role in the Dutch Revolt and contributions to classical studies.
  • B. Charles Dagomer
    Charles Dagomer was an 18th-century French artist and teacher known for instructing painter Jean-Baptiste Huet.
  • C. Victor Kubicek
    Victor Kubicek is a film producer best known for co-producing the science fiction action movie "Terminator Salvation."
  • D. Zhozef Kotin
    Zhozef Kotin was a prominent Soviet tank designer best known for leading the development of several heavy tanks used during World War II.
  • E. Peter Sova
    Peter Sova was a Czech-American cinematographer known for his stylish visual work on films such as "Lucky Number Slevin" and collaborations with directors like Barry Levinson.
  • 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_69c6887a499881909dd23341399c59d8 completed March 27, 2026, 1:39 p.m.
NER Named-entity recognition batch_69c6eb8a0b4881908ff27c5a75bd4a95 completed March 27, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7eedfa4d08190997a692b81309309 completed March 28, 2026, 3:08 p.m.
Created at: March 27, 2026, 3 p.m.