Triple

T4465087
Position Surface form Disambiguated ID Type / Status
Subject Mike Spano E98356 entity
Predicate spouse P13 FINISHED
Object Mary Calvi
Mary Calvi is an American television journalist and news anchor, best known for her work with WCBS-TV in New York City.
E441480 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: Mary Calvi | Statement: [Mike Spano, spouse, Mary Calvi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mary Calvi
Context triple: [Mike Spano, spouse, Mary Calvi]
  • A. June Duprez
    June Duprez was a British film actress best known for her roles in 1940s dramas and adventure films, including the classic "The Thief of Bagdad."
  • B. Yvette Guilbert
    Yvette Guilbert was a celebrated French cabaret singer and actress of the Belle Époque, renowned for her expressive performances and distinctive long black gloves.
  • C. Francie Calfo
    Francie Calfo is a fictional character from the television series "Alias," known for her close friendship with protagonist Sydney Bristow.
  • D. Maria Schneider
    Maria Schneider is a Grammy-winning American jazz composer and bandleader renowned for her innovative large-ensemble writing and genre-blending orchestral jazz.
  • E. Maria Schneider
    Maria Schneider was a French actress best known for her controversial and breakout role in Bernardo Bertolucci’s film "Last Tango in Paris."
  • 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: Mary Calvi
Triple: [Mike Spano, spouse, Mary Calvi]
Generated description
Mary Calvi is an American television journalist and news anchor, best known for her work with WCBS-TV in New York City.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mary Calvi
Target entity description: Mary Calvi is an American television journalist and news anchor, best known for her work with WCBS-TV in New York City.
  • A. June Duprez
    June Duprez was a British film actress best known for her roles in 1940s dramas and adventure films, including the classic "The Thief of Bagdad."
  • B. Yvette Guilbert
    Yvette Guilbert was a celebrated French cabaret singer and actress of the Belle Époque, renowned for her expressive performances and distinctive long black gloves.
  • C. Francie Calfo
    Francie Calfo is a fictional character from the television series "Alias," known for her close friendship with protagonist Sydney Bristow.
  • D. Maria Schneider
    Maria Schneider was a French actress best known for her controversial and breakout role in Bernardo Bertolucci’s film "Last Tango in Paris."
  • E. Maria Schneider
    Maria Schneider is a Grammy-winning American jazz composer and bandleader renowned for her innovative large-ensemble writing and genre-blending orchestral jazz.
  • 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_69b3454a7c608190944f5455c8031d73 completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b35697937c8190b91f72d9e4f945f6 completed March 13, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69b6285164b081908f144e74ae3a1be8 completed March 15, 2026, 3:32 a.m.
NEDg Description generation batch_69b62954b77c8190968f844514656415 completed March 15, 2026, 3:36 a.m.
NED2 Entity disambiguation (via description) batch_69b62a0cd92c8190a9eee2a9d73fb679 completed March 15, 2026, 3:39 a.m.
Created at: March 12, 2026, 11:34 p.m.