Triple

T2136728
Position Surface form Disambiguated ID Type / Status
Subject T. J. Holmes E46670 entity
Predicate spouse P13 FINISHED
Object Marilee Fiebig
Marilee Fiebig is an American attorney and immigration lawyer who has also worked as a fashion and entertainment industry executive.
E445645 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: Marilee Fiebig | Statement: [T. J. Holmes, spouse, Marilee Fiebig]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marilee Fiebig
Context triple: [T. J. Holmes, spouse, Marilee Fiebig]
  • A. Gail Klintworth
    Gail Klintworth is a business leader known for her senior roles in global consumer goods companies and her work advancing responsible, sustainable business practices.
  • B. Margaret Engemann
    Margaret Engemann was the wife of pioneering American mathematician and cybernetics founder Norbert Wiener.
  • C. Beverly Van Zile
    Beverly Van Zile is best known as the second wife of Apollo 11 astronaut Buzz Aldrin.
  • D. Colleen Ahland
    Colleen Ahland is a linguist known for her research on the Koman languages of Ethiopia and Sudan, focusing on their documentation, description, and classification.
  • E. Ann Dusenberry
    Ann Dusenberry is an American actress best known for her role in the thriller sequel "Jaws 2" and for her work in film and television during the 1970s and 1980s.
  • 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: Marilee Fiebig
Triple: [T. J. Holmes, spouse, Marilee Fiebig]
Generated description
Marilee Fiebig is an American attorney and immigration lawyer who has also worked as a fashion and entertainment industry executive.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marilee Fiebig
Target entity description: Marilee Fiebig is an American attorney and immigration lawyer who has also worked as a fashion and entertainment industry executive.
  • A. Gail Klintworth
    Gail Klintworth is a business leader known for her senior roles in global consumer goods companies and her work advancing responsible, sustainable business practices.
  • B. Margaret Engemann
    Margaret Engemann was the wife of pioneering American mathematician and cybernetics founder Norbert Wiener.
  • C. Beverly Van Zile
    Beverly Van Zile is best known as the second wife of Apollo 11 astronaut Buzz Aldrin.
  • D. Colleen Ahland
    Colleen Ahland is a linguist known for her research on the Koman languages of Ethiopia and Sudan, focusing on their documentation, description, and classification.
  • E. Ann Dusenberry
    Ann Dusenberry is an American actress best known for her role in the thriller sequel "Jaws 2" and for her work in film and television during the 1970s and 1980s.
  • 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_69a88a174ab48190a5db20c132e5dccf completed March 4, 2026, 7:37 p.m.
NER Named-entity recognition batch_69abbdff9254819094d27405478e29a0 completed March 7, 2026, 5:56 a.m.
NED1 Entity disambiguation (via context triple) batch_69bb60bff62881908ff53b9b02d9c869 completed March 19, 2026, 2:34 a.m.
NEDg Description generation batch_69bb6841dd7881909e946d9965c8509c completed March 19, 2026, 3:06 a.m.
NED2 Entity disambiguation (via description) batch_69bb68a42af4819089a6502187d6f22b completed March 19, 2026, 3:08 a.m.
Created at: March 4, 2026, 7:44 p.m.