Triple

T5766268
Position Surface form Disambiguated ID Type / Status
Subject Brian Eno E127220 entity
Predicate produced P490 FINISHED
Object Low E91544 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: Low | Statement: [Brian Eno, produced, Low]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Low
Context triple: [Brian Eno, produced, Low]
  • A. Low chosen
    Low is an American indie rock band from Duluth, Minnesota, known for their minimalist, slow-tempo sound and hushed vocal harmonies often associated with the "slowcore" genre.
  • B. LOWW
    LOWW is the ICAO airport code for Vienna International Airport, the main international gateway serving Vienna, Austria.
  • C. Low family
    The Low family is a prominent American mercantile and political dynasty historically linked to New York commerce and intermarried with influential families such as the Delanos.
  • D. Low Mass
    Low Mass is a simpler, typically quieter form of the traditional Latin Tridentine Mass celebrated by a priest with minimal ceremonial and usually without music.
  • E. Low Roar
    Low Roar was an Iceland-based ambient and post-rock music project by American musician Ryan Karazija, known for its atmospheric, melancholic soundscapes and prominent use in video game and film soundtracks.
  • 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_69c00834f6308190851b0abeddd8ed7e completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c02970db3481908a06941c9d59cc86 completed March 22, 2026, 5:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c07e5d8c8c819081067de808ac1b56 completed March 22, 2026, 11:42 p.m.
Created at: March 22, 2026, 3:49 p.m.