Triple

T20969101
Position Surface form Disambiguated ID Type / Status
Subject Michael Lewis E516447 entity
Predicate spouse P13 FINISHED
Object Tabitha Soren
Tabitha Soren is an American fine art photographer and former MTV News correspondent known for her conceptual and psychologically driven photographic projects.
E1460501 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: Tabitha Soren | Statement: [Michael Lewis, spouse, Tabitha Soren]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tabitha Soren
Context triple: [Michael Lewis, spouse, Tabitha Soren]
  • A. Tabitha Hunt
    Tabitha Hunt is one of the children of the late British Formula One world champion James Hunt.
  • B. Tabitha Grant
    Tabitha Grant is the daughter of British actor Hugh Grant and his former partner Tinglan Hong.
  • C. Beth Sully
    Beth Sully is known as the wife of American screenwriter and film producer Frank Butler.
  • D. Tiera Kennedy
    Tiera Kennedy is an American country singer-songwriter known for her soulful vocals and rising presence in contemporary country music.
  • E. Tessa Kennedy
    Tessa Kennedy is a British interior designer known for her high-profile projects and as the mother of actor Cary Elwes.
  • 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: Tabitha Soren
Triple: [Michael Lewis, spouse, Tabitha Soren]
Generated description
Tabitha Soren is an American fine art photographer and former MTV News correspondent known for her conceptual and psychologically driven photographic projects.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tabitha Soren
Target entity description: Tabitha Soren is an American fine art photographer and former MTV News correspondent known for her conceptual and psychologically driven photographic projects.
  • A. Tabitha Hunt
    Tabitha Hunt is one of the children of the late British Formula One world champion James Hunt.
  • B. Tabitha Grant
    Tabitha Grant is the daughter of British actor Hugh Grant and his former partner Tinglan Hong.
  • C. Beth Sully
    Beth Sully is known as the wife of American screenwriter and film producer Frank Butler.
  • D. Tiera Kennedy
    Tiera Kennedy is an American country singer-songwriter known for her soulful vocals and rising presence in contemporary country music.
  • E. Tessa Kennedy
    Tessa Kennedy is a British interior designer known for her high-profile projects and as the mother of actor Cary Elwes.
  • 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_69e0b4fee5ac8190875fa9ceba1a5e5e completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6fb9e3a50819085b3a974bda812e0 completed April 21, 2026, 4:22 a.m.
NED1 Entity disambiguation (via context triple) batch_6a092fb3e5088190bf842c0e7aabc14d completed May 17, 2026, 3:02 a.m.
NEDg Description generation batch_6a0930a5cffc8190a7d1cc19e5cacf49 completed May 17, 2026, 3:06 a.m.
NED2 Entity disambiguation (via description) batch_6a093133c77c8190a9e0326980c7717f completed May 17, 2026, 3:08 a.m.
Created at: April 16, 2026, 1:42 p.m.