Triple

T17687540
Position Surface form Disambiguated ID Type / Status
Subject Gerhart Eisler E440932 entity
Predicate spouse P13 FINISHED
Object Hede Massing
Hede Massing was an Austrian-born actress and Soviet intelligence agent who later became known for her testimony about communist espionage activities in the United States.
 E1282790 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: Hede Massing | Statement: [Gerhart Eisler, spouse, Hede Massing]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hede Massing
Context triple: [Gerhart Eisler, spouse, Hede Massing]
  • A. Lotte Andersen
    Lotte Andersen is a Danish actress known for her roles in Scandinavian film and television.
  • B. Christianne Jensen
    Christianne Jensen is a vocalist known for her guest appearance on Jon Bellion’s album "Glory Sound Prep."
  • C. Hanne Jacobsen
    Hanne Jacobsen is a Danish choreographer and former dancer best known as the longtime wife of actor Mads Mikkelsen.
  • D. Ingrid Knudsen
    Ingrid Knudsen is the woman targeted by a violent cult and safeguarded by tough cop Marion “Cobra” Cobretti in the 1986 action film "Cobra."
  • E. Eline Eriksen
    Eline Eriksen was a Danish artist’s model best known as the primary model for the iconic Little Mermaid statue in Copenhagen.
  • 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: Hede Massing
Triple: [Gerhart Eisler, spouse, Hede Massing]
Generated description
Hede Massing was an Austrian-born actress and Soviet intelligence agent who later became known for her testimony about communist espionage activities in the United States.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hede Massing
Target entity description: Hede Massing was an Austrian-born actress and Soviet intelligence agent who later became known for her testimony about communist espionage activities in the United States.
  • A. Lotte Andersen
    Lotte Andersen is a Danish actress known for her roles in Scandinavian film and television.
  • B. Christianne Jensen
    Christianne Jensen is a vocalist known for her guest appearance on Jon Bellion’s album "Glory Sound Prep."
  • C. Hanne Jacobsen
    Hanne Jacobsen is a Danish choreographer and former dancer best known as the longtime wife of actor Mads Mikkelsen.
  • D. Ingrid Knudsen
    Ingrid Knudsen is the woman targeted by a violent cult and safeguarded by tough cop Marion “Cobra” Cobretti in the 1986 action film "Cobra."
  • E. Eline Eriksen
    Eline Eriksen was a Danish artist’s model best known as the primary model for the iconic Little Mermaid statue in Copenhagen.
  • 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_69d8b9e940b081908b862bb0e6e89b0d completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e470488c4081909b747313ef97b69c completed April 19, 2026, 6:03 a.m.
NED1 Entity disambiguation (via context triple) batch_6a02232e1b4481908e8a89f2c1c244f1 completed May 11, 2026, 6:42 p.m.
NEDg Description generation batch_6a0224e2403881909a6f86bcad4ce7b3 completed May 11, 2026, 6:50 p.m.
NED2 Entity disambiguation (via description) batch_6a02254cbd3c8190afca986f066a60d2 completed May 11, 2026, 6:51 p.m.
Created at: April 10, 2026, 10:03 a.m.