Triple

T14285228
Position Surface form Disambiguated ID Type / Status
Subject Matty E354152 entity
Predicate relatedName P3889 FINISHED
Object Mat E354151 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: Mat | Statement: [Matty, relatedName, Mat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mat
Context triple: [Matty, relatedName, Mat]
  • A. Mat chosen
    Mat is a common shortened form of the given name Matthew, often used as an informal or familiar nickname.
  • B. MAT
    MAT is the commonly used abbreviation for the Moscow Art Theatre, a historic and influential Russian theatre company renowned for its pioneering work in modern drama and acting techniques.
  • C. Mart
    Mart is the given name of Mart Stam, a Dutch architect and furniture designer known for pioneering modernist and tubular steel chair designs.
  • D. Mate
    Mate is a Croatian entrepreneur and engineer best known as the founder and CEO of electric hypercar manufacturer Rimac Automobili.
  • E. Ma
    Ma is a fictional character appearing in Enid Blyton’s children’s adventure novel "The Circus of Adventure."
  • 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_69d8278e17088190b328c5a9d4be74ff completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de697ef40c8190bea37724b28c2e99 completed April 14, 2026, 4:21 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd3d1c4d988190b595e6a33ef96c28 completed May 8, 2026, 1:32 a.m.
Created at: April 10, 2026, 1:10 a.m.