Triple

T10338579
Position Surface form Disambiguated ID Type / Status
Subject Tom Hagen E243069 entity
Predicate spouse P13 FINISHED
Object Theresa Hagen
Theresa Hagen is known as the wife of Tom Hagen, the fictional consigliere to the Corleone family in Mario Puzo's "The Godfather" series.
E856898 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: Theresa Hagen | Statement: [Tom Hagen, spouse, Theresa Hagen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Theresa Hagen
Context triple: [Tom Hagen, spouse, Theresa Hagen]
  • A. Dena Dietrich
    Dena Dietrich was an American actress best known for her television work and iconic “Mother Nature” margarine commercials in the 1970s.
  • B. Bobbie Carle
    Bobbie Carle is best known as the wife of celebrated children's book author and illustrator Eric Carle.
  • C. Lea Hurst
    Lea Hurst is a historic country house in Derbyshire, England, best known as the childhood home of Florence Nightingale.
  • D. Tiffy Gerhardt
    Tiffy Gerhardt is a central character in the television drama series "The Unit," known for her role as the outspoken and resilient wife of one of the elite soldiers.
  • E. Patty Dann
    Patty Dann is an American novelist and memoirist best known for writing the coming-of-age novel "Mermaids," which was adapted into a popular 1990 film.
  • 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: Theresa Hagen
Triple: [Tom Hagen, spouse, Theresa Hagen]
Generated description
Theresa Hagen is known as the wife of Tom Hagen, the fictional consigliere to the Corleone family in Mario Puzo's "The Godfather" series.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Theresa Hagen
Target entity description: Theresa Hagen is known as the wife of Tom Hagen, the fictional consigliere to the Corleone family in Mario Puzo's "The Godfather" series.
  • A. Dena Dietrich
    Dena Dietrich was an American actress best known for her television work and iconic “Mother Nature” margarine commercials in the 1970s.
  • B. Bobbie Carle
    Bobbie Carle is best known as the wife of celebrated children's book author and illustrator Eric Carle.
  • C. Lea Hurst
    Lea Hurst is a historic country house in Derbyshire, England, best known as the childhood home of Florence Nightingale.
  • D. Tiffy Gerhardt
    Tiffy Gerhardt is a central character in the television drama series "The Unit," known for her role as the outspoken and resilient wife of one of the elite soldiers.
  • E. Patty Dann
    Patty Dann is an American novelist and memoirist best known for writing the coming-of-age novel "Mermaids," which was adapted into a popular 1990 film.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a470948190959f298dd6110bf3 completed April 7, 2026, 10:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7506278f881908b090b13706e5d4e completed April 9, 2026, 7:08 a.m.
NEDg Description generation batch_69d75133588c819093af59327b951cd7 completed April 9, 2026, 7:11 a.m.
NED2 Entity disambiguation (via description) batch_69d751d94a7081909fbe78fb6f76aef5 completed April 9, 2026, 7:14 a.m.
Created at: April 6, 2026, 11:54 a.m.