Triple

T21204067
Position Surface form Disambiguated ID Type / Status
Subject Mart Laar E522531 entity
Predicate givenName P17 FINISHED
Object Mart 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: Mart | Statement: [Mart Laar, givenName, Mart]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mart
Context triple: [Mart Laar, givenName, Mart]
  • A. Mart chosen
    Mart is the given name of Mart Stam, a Dutch architect and furniture designer known for pioneering modernist and tubular steel chair designs.
  • B. Mart
    Mart is a prominent modern and contemporary art museum based in Rovereto, Italy, known for its extensive collections and cultural programming.
  • C. Mer
    Mer is a small coral island in the eastern Torres Strait of Australia, known as the home of the Meriam people and central to the landmark native title case brought by Eddie Mabo.
  • D. Mer
    Mer is a small commune in central France located in the Loir-et-Cher department, known for its proximity to the Loire River and several historic châteaux.
  • E. Mate
    Mate is a Croatian entrepreneur and engineer best known as the founder and CEO of electric hypercar manufacturer Rimac Automobili.
  • 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_69e0b5112d8881909510b2dcdc93106d completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e7343367308190b1b772d3c8e25dcb completed April 21, 2026, 8:24 a.m.
Created at: April 16, 2026, 3:19 p.m.