Triple

T12655931
Position Surface form Disambiguated ID Type / Status
Subject Marie Tussaud E302282 entity
Predicate familyName P18 FINISHED
Object Grosholtz
Grosholtz is the original family surname of famed wax sculptor Marie Tussaud, used before she became widely known under her married name.
 E995305 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: Grosholtz | Statement: [Marie Tussaud, familyName, Grosholtz]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Grosholtz
Context triple: [Marie Tussaud, familyName, Grosholtz]
  • A. Rothkowitz
    Rothkowitz is the original family surname of the abstract expressionist painter Mark Rothko, reflecting his Eastern European Jewish heritage.
  • B. Levshitz
    Levshitz is an alternative transliteration of the Russian surname Lifshitz, commonly associated with several notable scientists and intellectuals.
  • C. Grinevsky
    Grinevsky is the original surname of Russian writer Alexander Grin, known for his romantic and adventure fiction.
  • D. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • E. Orlovsky
    Orlovsky is a surname most notably associated with Peter Orlovsky, the American poet and longtime partner of Beat Generation writer Allen Ginsberg.
  • 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: Grosholtz
Triple: [Marie Tussaud, familyName, Grosholtz]
Generated description
Grosholtz is the original family surname of famed wax sculptor Marie Tussaud, used before she became widely known under her married name.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Grosholtz
Target entity description: Grosholtz is the original family surname of famed wax sculptor Marie Tussaud, used before she became widely known under her married name.
  • A. Rothkowitz
    Rothkowitz is the original family surname of the abstract expressionist painter Mark Rothko, reflecting his Eastern European Jewish heritage.
  • B. Levshitz
    Levshitz is an alternative transliteration of the Russian surname Lifshitz, commonly associated with several notable scientists and intellectuals.
  • C. Grinevsky
    Grinevsky is the original surname of Russian writer Alexander Grin, known for his romantic and adventure fiction.
  • D. Joffe
    Joffe is a surname most notably associated with Adolf Joffe, a prominent early 20th-century Russian revolutionary and diplomat.
  • E. Orlovsky
    Orlovsky is a surname most notably associated with Peter Orlovsky, the American poet and longtime partner of Beat Generation writer Allen Ginsberg.
  • 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_69d7bded71a88190bb76e2413af9ea66 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d961620b188190a8a8569f1133a9cf completed April 10, 2026, 8:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69f668832c7081909eb75429efba493e completed May 2, 2026, 9:11 p.m.
NEDg Description generation batch_69f6697e3a688190abd025df1112feba completed May 2, 2026, 9:15 p.m.
NED2 Entity disambiguation (via description) batch_69f66a9230608190bfe99290ca1679fa completed May 2, 2026, 9:20 p.m.
Created at: April 9, 2026, 5:18 p.m.