Triple

T20854841
Position Surface form Disambiguated ID Type / Status
Subject Gustavian era E513451 entity
Predicate hasWriter P4244 FINISHED
Object Carl Michael Bellman 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: Carl Michael Bellman | Statement: [Gustavian era, hasWriter, Carl Michael Bellman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carl Michael Bellman
Context triple: [Gustavian era, hasWriter, Carl Michael Bellman]
  • A. Carl Michael Bellman chosen
    Carl Michael Bellman was an 18th-century Swedish poet, songwriter, and performer renowned for his lyrical and often humorous songs depicting Stockholm life and tavern culture.
  • B. Ulf Lundell
    Ulf Lundell is a Swedish rock musician, songwriter, and author, often regarded as one of Sweden’s most influential rock artists.
  • C. Gustaf Banér
    Gustaf Banér was a Swedish nobleman and statesman who served on the royal council before being executed during the Linköping Bloodbath in 1600.
  • D. Ben Boye
    Ben Boye is an American multi-instrumentalist and session musician known for his work on piano and keyboards in indie folk and experimental music collaborations.
  • E. Kjell Bäckman
    Kjell Bäckman was a Swedish speed skater and Olympic medalist renowned for his achievements in long-distance events during the late 1950s and early 1960s.
  • 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_69e0b4f5b01081909452f654d2fc3f50 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c3a7113c819087994bcdfe643bc1 completed April 21, 2026, 12:24 a.m.
Created at: April 16, 2026, 12:44 p.m.