Triple

T5830578
Position Surface form Disambiguated ID Type / Status
Subject Henry van de Velde E129333 entity
Predicate spouse P13 FINISHED
Object Maria Sèthe
Maria Sèthe was the wife and muse of Belgian architect and designer Henry van de Velde, known for her role in his artistic circle and early modernist milieu.
E550761 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: Maria Sèthe | Statement: [Henry van de Velde, spouse, Maria Sèthe]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Maria Sèthe
Context triple: [Henry van de Velde, spouse, Maria Sèthe]
  • A. Renée
    Renée is a feminine given name of French origin, commonly used in French-speaking countries and beyond.
  • B. Maria Magdalena Keverich
    Maria Magdalena Keverich was a German woman best known as the mother of the composer Ludwig van Beethoven.
  • C. Liliane
    Liliane is a feminine given name of French origin, notably borne by French heiress and businesswoman Liliane Bettencourt.
  • D. Odile
    Odile is the seductive and deceptive Black Swan character in the ballet "Swan Lake," often portrayed as the antagonist and foil to the virtuous Odette.
  • E. Bettina
    Bettina is a feminine given name of Hebrew origin, often considered a diminutive of Elisabeth or Benedetta and used in various European languages.
  • 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: Maria Sèthe
Triple: [Henry van de Velde, spouse, Maria Sèthe]
Generated description
Maria Sèthe was the wife and muse of Belgian architect and designer Henry van de Velde, known for her role in his artistic circle and early modernist milieu.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Maria Sèthe
Target entity description: Maria Sèthe was the wife and muse of Belgian architect and designer Henry van de Velde, known for her role in his artistic circle and early modernist milieu.
  • A. Renée
    Renée is a feminine given name of French origin, commonly used in French-speaking countries and beyond.
  • B. Maria Magdalena Keverich
    Maria Magdalena Keverich was a German woman best known as the mother of the composer Ludwig van Beethoven.
  • C. Liliane
    Liliane is a feminine given name of French origin, notably borne by French heiress and businesswoman Liliane Bettencourt.
  • D. Odile
    Odile is the seductive and deceptive Black Swan character in the ballet "Swan Lake," often portrayed as the antagonist and foil to the virtuous Odette.
  • E. Bettina
    Bettina is a feminine given name of Hebrew origin, often considered a diminutive of Elisabeth or Benedetta and used in various European languages.
  • 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_69c00849d55481908b4f9f5543e0bf6d completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c0346ac31c8190bbd28444f75da875 completed March 22, 2026, 6:26 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0a18c48588190b4848dff1c277079 completed March 23, 2026, 2:12 a.m.
NEDg Description generation batch_69c0a33036bc8190b7c0b453a1d8f319 completed March 23, 2026, 2:19 a.m.
NED2 Entity disambiguation (via description) batch_69c0a38522f0819085514ae6f41c5991 completed March 23, 2026, 2:20 a.m.
Created at: March 22, 2026, 3:54 p.m.