Triple

T9552974
Position Surface form Disambiguated ID Type / Status
Subject Bror Blixen E230467 entity
Predicate familyName P18 FINISHED
Object Blixen
Blixen is a Danish surname most famously associated with author Karen Blixen, known internationally as Isak Dinesen.
E807057 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: Blixen | Statement: [Bror Blixen, familyName, Blixen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Blixen
Context triple: [Bror Blixen, familyName, Blixen]
  • A. Tine Havelaar
    Tine Havelaar is a character in Multatuli’s novel "Max Havelaar," depicted as the devoted and morally upright wife of the protagonist.
  • B. Rosmersholm
    Rosmersholm is a late 19th-century drama by Henrik Ibsen that explores themes of guilt, political idealism, and the oppressive weight of tradition within a decaying aristocratic household.
  • C. The Brow
    The Brow is a grotesque, criminal mastermind and one of the most notorious villains in the Dick Tracy comic strip series.
  • D. The Brow
    The Brow is the widely recognized nickname of NBA star Anthony Davis, referring to his distinctive unibrow and used as a personal brand in his basketball career.
  • E. Muriel
    Muriel is a feminine given name of French origin that has been borne by various notable figures, including politicians, writers, and artists.
  • 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: Blixen
Triple: [Bror Blixen, familyName, Blixen]
Generated description
Blixen is a Danish surname most famously associated with author Karen Blixen, known internationally as Isak Dinesen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Blixen
Target entity description: Blixen is a Danish surname most famously associated with author Karen Blixen, known internationally as Isak Dinesen.
  • A. Tine Havelaar
    Tine Havelaar is a character in Multatuli’s novel "Max Havelaar," depicted as the devoted and morally upright wife of the protagonist.
  • B. Rosmersholm
    Rosmersholm is a late 19th-century drama by Henrik Ibsen that explores themes of guilt, political idealism, and the oppressive weight of tradition within a decaying aristocratic household.
  • C. The Brow
    The Brow is a grotesque, criminal mastermind and one of the most notorious villains in the Dick Tracy comic strip series.
  • D. The Brow
    The Brow is the widely recognized nickname of NBA star Anthony Davis, referring to his distinctive unibrow and used as a personal brand in his basketball career.
  • E. Muriel
    Muriel is a feminine given name of French origin that has been borne by various notable figures, including politicians, writers, and artists.
  • 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_69ca847d3be8819099c9dad2a7e786f1 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99217de48190b528e14fd02ee987 completed April 1, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69d15286f7c881909258b9f06a81e464 completed April 4, 2026, 6:03 p.m.
NEDg Description generation batch_69d154e80dc081909af88042ef0bebce completed April 4, 2026, 6:14 p.m.
NED2 Entity disambiguation (via description) batch_69d155977ab481908951906946b74248 completed April 4, 2026, 6:16 p.m.
Created at: March 30, 2026, 8:02 p.m.