Triple

T20817051
Position Surface form Disambiguated ID Type / Status
Subject Harry E512466 entity
Predicate executiveProducer P7225 FINISHED
Object Jeanne Romano
Jeanne Romano is a television and film producer known for her work as an executive producer on projects associated with Harry.
E1455766 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: Jeanne Romano | Statement: [Harry, executiveProducer, Jeanne Romano]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Jeanne Romano
Context triple: [Harry, executiveProducer, Jeanne Romano]
  • A. Jeannine Bisignano
    Jeannine Bisignano is known as the former wife of American actor Michael Madsen.
  • B. Lorraine Vitale
    Lorraine Vitale is the longtime wife of famed American basketball sportscaster Dick Vitale and a prominent partner in his charitable and community endeavors.
  • C. Carole Rome
    Carole Rome is an American businesswoman best known as the wife of former Florida governor and U.S. congressman Charlie Crist.
  • D. Jeanne Vander Myde
    Jeanne Vander Myde is best known as the wife of the late U.S. Senator John Warner of Virginia.
  • E. Roberta Romano
    Roberta Romano is a prominent American legal scholar known for her influential work on corporate law and governance, and for serving as a long-time professor at Yale Law School.
  • 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: Jeanne Romano
Triple: [Harry, executiveProducer, Jeanne Romano]
Generated description
Jeanne Romano is a television and film producer known for her work as an executive producer on projects associated with Harry.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Jeanne Romano
Target entity description: Jeanne Romano is a television and film producer known for her work as an executive producer on projects associated with Harry.
  • A. Jeannine Bisignano
    Jeannine Bisignano is known as the former wife of American actor Michael Madsen.
  • B. Lorraine Vitale
    Lorraine Vitale is the longtime wife of famed American basketball sportscaster Dick Vitale and a prominent partner in his charitable and community endeavors.
  • C. Carole Rome
    Carole Rome is an American businesswoman best known as the wife of former Florida governor and U.S. congressman Charlie Crist.
  • D. Jeanne Vander Myde
    Jeanne Vander Myde is best known as the wife of the late U.S. Senator John Warner of Virginia.
  • E. Roberta Romano
    Roberta Romano is a prominent American legal scholar known for her influential work on corporate law and governance, and for serving as a long-time professor at Yale Law School.
  • 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_69e0b4cd25088190b48ca9700cd24efc completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2f3473c81908c43a2ec242b1acd completed April 21, 2026, 12:21 a.m.
NED1 Entity disambiguation (via context triple) batch_6a09138bea448190853e3193cc033bb2 completed May 17, 2026, 1:02 a.m.
NEDg Description generation batch_6a0914ad125c8190bc629321ec2a3a1b completed May 17, 2026, 1:06 a.m.
NED2 Entity disambiguation (via description) batch_6a09157461b4819096ab8d77b40f9c9a completed May 17, 2026, 1:10 a.m.
Created at: April 16, 2026, 12:41 p.m.