Triple

T11657490
Position Surface form Disambiguated ID Type / Status
Subject Sharp E277046 entity
Predicate brand P1500 FINISHED
Object Plasmacluster E383932 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: Plasmacluster | Statement: [Sharp, brand, Plasmacluster]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Plasmacluster
Context triple: [Sharp, brand, Plasmacluster]
  • A. Plasmacluster chosen
    Plasmacluster is Sharp Corporation’s proprietary air purification technology brand that uses ion generation to reduce airborne pollutants and improve indoor air quality.
  • B. Plasmolen
    Plasmolen is a small village in the Dutch province of Limburg, known for its scenic forests, hills, and recreational areas near the Maas River.
  • C. Plasmarl
    Plasmarl is a residential and industrial district in the city of Swansea, Wales, known for its proximity to the River Tawe and major transport routes.
  • D. Electryon
    Electryon is a king of Mycenae in Greek mythology, known primarily as the grandfather of the hero Heracles.
  • E. Spektr
    Spektr was a Russian-built science module of the Mir space station, primarily used for Earth observation and housing U.S. research equipment during the Shuttle–Mir program.
  • 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_69d6aafbb3c081908a9cdb4ecb8d981d completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a3d0331481909682b2e504e4c9a0 completed April 10, 2026, 7:16 a.m.
NED1 Entity disambiguation (via context triple) batch_69ee88166900819095063f045be44bed completed April 26, 2026, 9:48 p.m.
Created at: April 8, 2026, 9:39 p.m.