Triple

T17705179
Position Surface form Disambiguated ID Type / Status
Subject Tarkett Group E441411 entity
Predicate hasBrand P1500 FINISHED
Object Desso 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: Desso | Statement: [Tarkett Group, hasBrand, Desso]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Desso
Context triple: [Tarkett Group, hasBrand, Desso]
  • A. Desso chosen
    Desso is a Dutch company known for manufacturing high-quality carpets and artificial turf systems for commercial, residential, and sports applications.
  • B. Dosso
    Dosso is a key town in southwestern Niger that serves as an important regional and transportation hub.
  • C. Dunan
    Dunan is an alternative name for Yonaguni, a remote Japanese island in the Yaeyama archipelago known as the country’s westernmost point.
  • D. Burlata
    Burlata is a small municipality in the autonomous community of Navarre in northern Spain, situated just east of the regional capital Pamplona.
  • E. Dosse
    The Dosse is a river in northeastern Germany that flows through Brandenburg and Saxony-Anhalt before joining the Havel.
  • 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_69d8b9ea20b48190ace88bb46b01e6a9 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e47297359481909629c79220e58245 completed April 19, 2026, 6:13 a.m.
Created at: April 10, 2026, 10:05 a.m.