Triple

T504978
Position Surface form Disambiguated ID Type / Status
Subject Tim Burton E10483 entity
Predicate spouse P13 FINISHED
Object Lena Gieseke
Lena Gieseke is a German visual effects artist and academic known for her work in 3D animation and digital media.
 E67256 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: Lena Gieseke | Statement: [Tim Burton, spouse, Lena Gieseke]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Lena Gieseke
Context triple: [Tim Burton, spouse, Lena Gieseke]
  • A. Johanna Herting
    Johanna Herting was the wife of 19th-century civil engineer John A. Roebling, known for supporting him during his career designing pioneering suspension bridges such as the Brooklyn Bridge.
  • B. Katharina Gsell
    Katharina Gsell was the wife of the eminent Swiss mathematician Leonhard Euler and the daughter of Swiss painter Georg Gsell.
  • C. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • D. Britta Ernst
    Britta Ernst is a German politician of the Social Democratic Party (SPD) who has served as a state minister for education in several German states and is married to Chancellor Olaf Scholz.
  • E. Ingrid Mössinger
    Ingrid Mössinger is a German art historian and curator known for her influential leadership roles at major contemporary art institutions.
  • 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: Lena Gieseke
Triple: [Tim Burton, spouse, Lena Gieseke]
Generated description
Lena Gieseke is a German visual effects artist and academic known for her work in 3D animation and digital media.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Lena Gieseke
Target entity description: Lena Gieseke is a German visual effects artist and academic known for her work in 3D animation and digital media.
  • A. Johanna Herting
    Johanna Herting was the wife of 19th-century civil engineer John A. Roebling, known for supporting him during his career designing pioneering suspension bridges such as the Brooklyn Bridge.
  • B. Katharina Gsell
    Katharina Gsell was the wife of the eminent Swiss mathematician Leonhard Euler and the daughter of Swiss painter Georg Gsell.
  • C. Eva Schubach
    Eva Schubach is known as a former spouse of Gerhard Schröder, the one-time Chancellor of Germany.
  • D. Britta Ernst
    Britta Ernst is a German politician of the Social Democratic Party (SPD) who has served as a state minister for education in several German states and is married to Chancellor Olaf Scholz.
  • E. Ingrid Mössinger
    Ingrid Mössinger is a German art historian and curator known for her influential leadership roles at major contemporary art institutions.
  • 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_69a2e848adf881908e5e04f7af030093 completed Feb. 28, 2026, 1:06 p.m.
NER Named-entity recognition batch_69a2f149bd1c81908ff58ac504ace2bf completed Feb. 28, 2026, 1:44 p.m.
NED1 Entity disambiguation (via context triple) batch_69a4c66b91608190aff4623917cf3ae2 completed March 1, 2026, 11:06 p.m.
NEDg Description generation batch_69a4c735b70c8190b281c88bc8a4f888 completed March 1, 2026, 11:09 p.m.
NED2 Entity disambiguation (via description) batch_69a4c7a59c4881908d13d0f7eb0ba334 completed March 1, 2026, 11:11 p.m.
Created at: Feb. 28, 2026, 1:12 p.m.