Triple

T14159087
Position Surface form Disambiguated ID Type / Status
Subject Eddie Cahill E350889 entity
Predicate spouse P13 FINISHED
Object Nikki Uberti
Nikki Uberti is a makeup artist, model, and former fashion industry figure known for her work in editorial and commercial projects.
E1087019 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: Nikki Uberti | Statement: [Eddie Cahill, spouse, Nikki Uberti]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nikki Uberti
Context triple: [Eddie Cahill, spouse, Nikki Uberti]
  • A. Nikki Faber
    Nikki Faber is a fictional character from the television sitcom "Spin City," known as one of the quirky staffers working in the New York City mayor's office.
  • B. Nikki Budzinski
    Nikki Budzinski is an American Democratic politician and U.S. Representative from Illinois who previously worked as a labor and policy advisor.
  • C. Nicole Grimaudo
    Nicole Grimaudo is an Italian actress known for her work in film, television, and theater, including prominent roles in contemporary Italian cinema.
  • D. Nicole Trunfio
    Nicole Trunfio is an Australian model and fashion designer known for her work with major international brands and appearances on reality modeling competitions.
  • E. Nikki Satosky
    Nikki Satosky is a fictional character portrayed by actress Mara Wilson.
  • 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: Nikki Uberti
Triple: [Eddie Cahill, spouse, Nikki Uberti]
Generated description
Nikki Uberti is a makeup artist, model, and former fashion industry figure known for her work in editorial and commercial projects.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nikki Uberti
Target entity description: Nikki Uberti is a makeup artist, model, and former fashion industry figure known for her work in editorial and commercial projects.
  • A. Nikki Faber
    Nikki Faber is a fictional character from the television sitcom "Spin City," known as one of the quirky staffers working in the New York City mayor's office.
  • B. Nikki Budzinski
    Nikki Budzinski is an American Democratic politician and U.S. Representative from Illinois who previously worked as a labor and policy advisor.
  • C. Nicole Grimaudo
    Nicole Grimaudo is an Italian actress known for her work in film, television, and theater, including prominent roles in contemporary Italian cinema.
  • D. Nicole Trunfio
    Nicole Trunfio is an Australian model and fashion designer known for her work with major international brands and appearances on reality modeling competitions.
  • E. Nikki Satosky
    Nikki Satosky is a fictional character portrayed by actress Mara Wilson.
  • 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_69d8278775fc8190b0802d22ca2f495d completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de61377de48190a3470d28f0edd34a completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd2804956c81909409fba998a87866 completed May 8, 2026, 12:02 a.m.
NEDg Description generation batch_69fd2a8d7b0c81908c80de21f7922f0a completed May 8, 2026, 12:13 a.m.
NED2 Entity disambiguation (via description) batch_69fd2b0c9b188190a7f096429aa92419 completed May 8, 2026, 12:15 a.m.
Created at: April 10, 2026, 12:58 a.m.