Triple

T4867736
Position Surface form Disambiguated ID Type / Status
Subject So Long, Marianne E109011 entity
Predicate inspiredBy P9 FINISHED
Object Marianne Ihlen
Marianne Ihlen was a Norwegian woman best known as Leonard Cohen’s muse and former lover, immortalized in several of his songs and writings.
E479176 NE FINISHED

How this triple was built (4 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: [So Long, Marianne, inspiredBy, Marianne Ihlen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marianne Ihlen
Context triple: [So Long, Marianne, inspiredBy, Marianne Ihlen]
  • A. Hanne Grotjord
    Hanne Grotjord is the wife of Norwegian politician and former Prime Minister Thorbjørn Jagland.
  • B. Ingeborg Holm
    Ingeborg Holm is a character in Thomas Mann’s novella "Tonio Kröger," representing part of the bourgeois world that shapes the protagonist’s conflicted feelings about art and ordinary life.
  • C. Lotten Ramel
    Lotten Ramel is a Swedish actress and singer, known for her work in film, television, and theater and as the daughter of entertainer Povel Ramel.
  • D. Inger Skramstad
    Inger Skramstad is known as the spouse of Norwegian-American physicist and Nobel laureate Ivar Giaever.
  • E. Catharina Bolnes
    Catharina Bolnes was the wife of Dutch painter Johannes Vermeer and the mother of his many children, known primarily through her connection to the artist’s life and estate.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Marianne Ihlen
Triple: [So Long, Marianne, inspiredBy, Marianne Ihlen]
Generated description
Marianne Ihlen was a Norwegian woman best known as Leonard Cohen’s muse and former lover, immortalized in several of his songs and writings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marianne Ihlen
Target entity description: Marianne Ihlen was a Norwegian woman best known as Leonard Cohen’s muse and former lover, immortalized in several of his songs and writings.
  • A. Hanne Grotjord
    Hanne Grotjord is the wife of Norwegian politician and former Prime Minister Thorbjørn Jagland.
  • B. Ingeborg Holm
    Ingeborg Holm is a character in Thomas Mann’s novella "Tonio Kröger," representing part of the bourgeois world that shapes the protagonist’s conflicted feelings about art and ordinary life.
  • C. Lotten Ramel
    Lotten Ramel is a Swedish actress and singer, known for her work in film, television, and theater and as the daughter of entertainer Povel Ramel.
  • D. Inger Skramstad
    Inger Skramstad is known as the spouse of Norwegian-American physicist and Nobel laureate Ivar Giaever.
  • E. Catharina Bolnes
    Catharina Bolnes was the wife of Dutch painter Johannes Vermeer and the mother of his many children, known primarily through her connection to the artist’s life and estate.
  • F. None of above. chosen

Provenance (5 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_69bd440d96a48190b0c87069adef2af1 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6d7bb0b88190bbc24498619910fc completed March 20, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69be6fb25f008190ab9b7cc904b540c9 completed March 21, 2026, 10:15 a.m.
NEDg Description generation batch_69be71ef01148190af12e1b9a2869612 completed March 21, 2026, 10:24 a.m.
NED2 Entity disambiguation (via description) batch_69be7242fc5c8190bc63ad852f937590 completed March 21, 2026, 10:26 a.m.
Created at: March 20, 2026, 1:26 p.m.