Triple

T405882
Position Surface form Disambiguated ID Type / Status
Subject Maye Musk E9381 entity
Predicate hasSibling P363 FINISHED
Object Kaye Haldeman
Kaye Haldeman is a member of the Musk family and the sister of model and dietitian Maye Musk.
E53849 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: Kaye Haldeman | Statement: [Maye Musk, hasSibling, Kaye Haldeman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kaye Haldeman
Context triple: [Maye Musk, hasSibling, Kaye Haldeman]
  • A. Maye Haldeman
    Maye Haldeman is a Canadian-South African model and dietitian best known as Maye Musk, the mother of entrepreneur Elon Musk and a prominent figure in fashion and nutrition.
  • B. Karen Verne
    Karen Verne was a German-born actress who appeared in Hollywood films of the 1940s and was once married to actor Peter Lorre.
  • C. Judith Nelson
    Judith Nelson was an American soprano known for her pioneering work and acclaimed performances in the early music and Baroque repertoire.
  • D. Janet Asimov
    Janet Asimov was an American psychiatrist, psychoanalyst, and science fiction writer who collaborated with and was married to author Isaac Asimov.
  • E. C. E. Webber
    C. E. Webber was a British television writer and script editor credited with helping develop the original concept and format of the long-running science fiction series Doctor Who.
  • 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: Kaye Haldeman
Triple: [Maye Musk, hasSibling, Kaye Haldeman]
Generated description
Kaye Haldeman is a member of the Musk family and the sister of model and dietitian Maye Musk.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kaye Haldeman
Target entity description: Kaye Haldeman is a member of the Musk family and the sister of model and dietitian Maye Musk.
  • A. Maye Haldeman chosen
    Maye Haldeman is a Canadian-South African model and dietitian best known as Maye Musk, the mother of entrepreneur Elon Musk and a prominent figure in fashion and nutrition.
  • B. Karen Verne
    Karen Verne was a German-born actress who appeared in Hollywood films of the 1940s and was once married to actor Peter Lorre.
  • C. Judith Nelson
    Judith Nelson was an American soprano known for her pioneering work and acclaimed performances in the early music and Baroque repertoire.
  • D. Janet Asimov
    Janet Asimov was an American psychiatrist, psychoanalyst, and science fiction writer who collaborated with and was married to author Isaac Asimov.
  • E. C. E. Webber
    C. E. Webber was a British television writer and script editor credited with helping develop the original concept and format of the long-running science fiction series Doctor Who.
  • F. None of above.

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_69a2e8004cb88190b92ed1add6abf41a completed Feb. 28, 2026, 1:05 p.m.
NER Named-entity recognition batch_69a2ecbc00508190bbb602179273f29c completed Feb. 28, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_69a431dd98dc8190a0020cdbeec5cfbf completed March 1, 2026, 12:32 p.m.
NEDg Description generation batch_69a43267c1d081908b2036402ce0ec11 completed March 1, 2026, 12:34 p.m.
NED2 Entity disambiguation (via description) batch_69a432f94a948190a958bba70c2fc806 completed March 1, 2026, 12:37 p.m.
Created at: Feb. 28, 2026, 1:08 p.m.