Triple

T22416987
Position Surface form Disambiguated ID Type / Status
Subject Magnus Gabriel De la Gardie E554147 entity
Predicate givenName P17 FINISHED
Object Magnus Gabriel 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: Magnus Gabriel | Statement: [Magnus Gabriel De la Gardie, givenName, Magnus Gabriel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Magnus Gabriel
Context triple: [Magnus Gabriel De la Gardie, givenName, Magnus Gabriel]
  • A. Magnus Gabriel chosen
    Magnus Gabriel was a prominent 17th-century Swedish statesman and nobleman from the influential De la Gardie family.
  • B. Magnus Volk
    Magnus Volk was a British electrical engineer and inventor best known for pioneering electric railways, including creating one of the world’s oldest operating electric railways in Brighton.
  • C. Magnus Barefoot
    Magnus Barefoot was a late 11th-century king of Norway known for his aggressive expansionist campaigns in the British Isles and his role in consolidating Norwegian royal power.
  • D. Magnus Manske
    Magnus Manske is a German software developer and biochemist best known for creating the original version of the MediaWiki software that powers Wikipedia.
  • E. Magnus Moan
    Magnus Moan is a Norwegian Nordic combined skier who has won multiple Olympic and World Championship medals in the sport.
  • 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_69e11e4e6ce8819085a1e06d886bf21c completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15946cd2c8190bdec0348de6ebcb9 completed April 29, 2026, 1:05 a.m.
Created at: April 16, 2026, 8:46 p.m.