Triple

T9244296
Position Surface form Disambiguated ID Type / Status
Subject Fanny Hensel E222147 entity
Predicate spouse P13 FINISHED
Object Wilhelm Hensel
Wilhelm Hensel was a 19th-century German portrait painter and draughtsman associated with the Berlin art scene and the Mendelssohn family circle.
 E786899 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: Wilhelm Hensel | Statement: [Fanny Hensel, spouse, Wilhelm Hensel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wilhelm Hensel
Context triple: [Fanny Hensel, spouse, Wilhelm Hensel]
  • A. Hermann Reinecke
    Hermann Reinecke was a German general and Nazi official who oversaw prisoner-of-war affairs in the Wehrmacht and was later convicted for war crimes committed under his authority.
  • B. Alfred Koerner
    Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
  • C. Walter Schumann
    Walter Schumann was an American composer and conductor best known for creating the iconic theme music for the television series Dragnet.
  • D. Paul Hensel
    Paul Hensel was a German philosopher known for his work in neo-Kantianism and as an academic mentor to figures such as Hans Reichenbach.
  • E. Carl Reinecke
    Carl Reinecke was a 19th-century German composer, conductor, pianist, and influential music educator associated with the Leipzig Conservatory.
  • 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: Wilhelm Hensel
Triple: [Fanny Hensel, spouse, Wilhelm Hensel]
Generated description
Wilhelm Hensel was a 19th-century German portrait painter and draughtsman associated with the Berlin art scene and the Mendelssohn family circle.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wilhelm Hensel
Target entity description: Wilhelm Hensel was a 19th-century German portrait painter and draughtsman associated with the Berlin art scene and the Mendelssohn family circle.
  • A. Hermann Reinecke
    Hermann Reinecke was a German general and Nazi official who oversaw prisoner-of-war affairs in the Wehrmacht and was later convicted for war crimes committed under his authority.
  • B. Alfred Koerner
    Alfred Koerner was an architect known for his work on the Berlin Botanical Garden.
  • C. Walter Schumann
    Walter Schumann was an American composer and conductor best known for creating the iconic theme music for the television series Dragnet.
  • D. Paul Hensel
    Paul Hensel was a German philosopher known for his work in neo-Kantianism and as an academic mentor to figures such as Hans Reichenbach.
  • E. Carl Reinecke
    Carl Reinecke was a 19th-century German composer, conductor, pianist, and influential music educator associated with the Leipzig Conservatory.
  • 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_69ca83ee26cc81909ac624e190597d6d completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69cd03edd37481908ea2f6dac354f04f completed April 1, 2026, 11:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d077e977c48190ba46a48850a3da0a completed April 4, 2026, 2:31 a.m.
NEDg Description generation batch_69d07c3d6c1881908b267c2947b360d6 completed April 4, 2026, 2:49 a.m.
NED2 Entity disambiguation (via description) batch_69d07ca8bad48190a0d36c6deb96610f completed April 4, 2026, 2:51 a.m.
Created at: March 30, 2026, 7:30 p.m.