Triple

T19664511
Position Surface form Disambiguated ID Type / Status
Subject Songs from a Room E472165 entity
Predicate coverArtFeatures P15270 FINISHED
Object Marianne Ihlen 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: Marianne Ihlen | Statement: [Songs from a Room, coverArtFeatures, Marianne Ihlen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marianne Ihlen
Context triple: [Songs from a Room, coverArtFeatures, Marianne Ihlen]
  • A. Marianne Ihlen chosen
    Marianne Ihlen was a Norwegian woman best known as Leonard Cohen’s muse and former lover, immortalized in several of his songs and writings.
  • B. Astrid Cleve
    Astrid Cleve was a Swedish botanist, chemist, and geologist noted as one of the first women in Sweden to earn a doctorate in science and for her pioneering work in diatom research.
  • C. Louise Lunde
    Louise Lunde is known as the spouse of American character actor Lance Henriksen.
  • D. Ghita Nørby
    Ghita Nørby is a renowned Danish actress celebrated for her extensive film, television, and theater career, making her one of Denmark’s most prominent and respected performers.
  • E. Marian Saastad Ottesen
    Marian Saastad Ottesen is a Norwegian actress known for her prominent role in the comedy-drama television series "Lilyhammer" and for her work in Norwegian film and theater.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416749d48190b141a6acd20c9694 completed April 20, 2026, 3:08 p.m.
Created at: April 10, 2026, 1:45 p.m.