Triple

T14068627
Position Surface form Disambiguated ID Type / Status
Subject Paul Cellucci E338541 entity
Predicate spouse P13 FINISHED
Object Janet Cellucci
Janet Cellucci is best known as the wife of former Massachusetts governor and U.S. ambassador to Canada Paul Cellucci.
E1096886 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: Janet Cellucci | Statement: [Paul Cellucci, spouse, Janet Cellucci]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Janet Cellucci
Context triple: [Paul Cellucci, spouse, Janet Cellucci]
  • A. Janet Healy
    Janet Healy is a film producer known for her work on animated features, including the 2012 adaptation of Dr. Seuss's "The Lorax."
  • B. Janine LaManna
    Janine LaManna is an American actress known for her work in film and on stage, including a role in the romantic comedy "Two Weeks Notice."
  • C. Janet Leahy
    Janet Leahy is an American television writer and producer known for her work on acclaimed series such as Mad Men.
  • D. Lynn Brunelle
    Lynn Brunelle is an Emmy Award–winning writer, educator, and former cast member of the Seattle-based sketch comedy show "Almost Live!" known for her work in science communication and children's media.
  • E. Nancy Shevell
    Nancy Shevell is an American businesswoman and heiress best known for her long-term relationship and marriage to musician Paul McCartney.
  • 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: Janet Cellucci
Triple: [Paul Cellucci, spouse, Janet Cellucci]
Generated description
Janet Cellucci is best known as the wife of former Massachusetts governor and U.S. ambassador to Canada Paul Cellucci.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Janet Cellucci
Target entity description: Janet Cellucci is best known as the wife of former Massachusetts governor and U.S. ambassador to Canada Paul Cellucci.
  • A. Janet Healy
    Janet Healy is a film producer known for her work on animated features, including the 2012 adaptation of Dr. Seuss's "The Lorax."
  • B. Janine LaManna
    Janine LaManna is an American actress known for her work in film and on stage, including a role in the romantic comedy "Two Weeks Notice."
  • C. Janet Leahy
    Janet Leahy is an American television writer and producer known for her work on acclaimed series such as Mad Men.
  • D. Lynn Brunelle
    Lynn Brunelle is an Emmy Award–winning writer, educator, and former cast member of the Seattle-based sketch comedy show "Almost Live!" known for her work in science communication and children's media.
  • E. Nancy Shevell
    Nancy Shevell is an American businesswoman and heiress best known for her long-term relationship and marriage to musician Paul McCartney.
  • 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_69d81c67ba6c819091935650dfb3b895 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de568d0404819087e0fe37c72162cb completed April 14, 2026, 3 p.m.
NED1 Entity disambiguation (via context triple) batch_69fd54fa19c081908e6467ee7b79f02a completed May 8, 2026, 3:14 a.m.
NEDg Description generation batch_69fd55fe4e1881909b4a973dc7deb22b completed May 8, 2026, 3:18 a.m.
NED2 Entity disambiguation (via description) batch_69fd568784788190b6a97c29814b7459 completed May 8, 2026, 3:20 a.m.
Created at: April 9, 2026, 10:21 p.m.