Triple

T13702870
Position Surface form Disambiguated ID Type / Status
Subject Jawbreaker E328562 entity
Predicate producer P490 FINISHED
Object Patricia Herskovic
Patricia Herskovic is a film producer best known for her work on the dark teen comedy "Jawbreaker."
E1075768 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: Patricia Herskovic | Statement: [Jawbreaker, producer, Patricia Herskovic]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Patricia Herskovic
Context triple: [Jawbreaker, producer, Patricia Herskovic]
  • A. Patricia Roccuzzo
    Patricia Roccuzzo is the maternal grandmother of Thiago Messi, the eldest son of footballer Lionel Messi and Antonela Roccuzzo.
  • B. Patricia Molin
    Patricia Molin is known as the spouse of American film and television editor and director Bud Molin.
  • C. Patricia Romanowski
    Patricia Romanowski is an American writer and ghostwriter best known for co-authoring autobiographies and memoirs for prominent musicians and entertainers.
  • D. Patricia Danova
    Patricia Danova is known as the spouse of Italian-American actor Cesare Danova.
  • E. Patricia Herrera
    Patricia Herrera is a Venezuelan-born fashion figure and daughter of renowned designer Carolina Herrera, known for her involvement in the fashion and arts world.
  • 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: Patricia Herskovic
Triple: [Jawbreaker, producer, Patricia Herskovic]
Generated description
Patricia Herskovic is a film producer best known for her work on the dark teen comedy "Jawbreaker."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Patricia Herskovic
Target entity description: Patricia Herskovic is a film producer best known for her work on the dark teen comedy "Jawbreaker."
  • A. Patricia Roccuzzo
    Patricia Roccuzzo is the maternal grandmother of Thiago Messi, the eldest son of footballer Lionel Messi and Antonela Roccuzzo.
  • B. Patricia Molin
    Patricia Molin is known as the spouse of American film and television editor and director Bud Molin.
  • C. Patricia Romanowski
    Patricia Romanowski is an American writer and ghostwriter best known for co-authoring autobiographies and memoirs for prominent musicians and entertainers.
  • D. Patricia Danova
    Patricia Danova is known as the spouse of Italian-American actor Cesare Danova.
  • E. Patricia Herrera
    Patricia Herrera is a Venezuelan-born fashion figure and daughter of renowned designer Carolina Herrera, known for her involvement in the fashion and arts world.
  • 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_69d8076ff62081908a7bd79889edd7a0 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69dcad162158819089280ee1e6b5c2cf completed April 13, 2026, 8:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69fbc315ff848190a6c8cbd5b90db7fc completed May 6, 2026, 10:39 p.m.
NEDg Description generation batch_69fc43c344c08190b5afa023f5009cb4 completed May 7, 2026, 7:48 a.m.
NED2 Entity disambiguation (via description) batch_69fc444a30a48190a2f65afcd5424d14 completed May 7, 2026, 7:50 a.m.
Created at: April 9, 2026, 9:54 p.m.