Triple

T14778064
Position Surface form Disambiguated ID Type / Status
Subject Starving E347314 entity
Predicate writer P1360 FINISHED
Object Christopher Petrosino
Christopher Petrosino is a writer associated with the work "Starving."
E1132638 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: Christopher Petrosino | Statement: [Starving, writer, Christopher Petrosino]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Christopher Petrosino
Context triple: [Starving, writer, Christopher Petrosino]
  • A. John Ficarra
    John Ficarra is an American humor writer and longtime editor-in-chief of Mad magazine, known for shaping its satirical voice for decades.
  • B. Joe Venafro
    Joe Venafro is a television producer best known for serving as an executive producer on the reality law-enforcement series "Live PD."
  • C. Tony DeMarco
    Tony DeMarco was an American professional boxer and former world welterweight champion known for his aggressive, crowd-pleasing fighting style during the 1950s.
  • D. Angelo Petraglia
    Angelo Petraglia is an American songwriter and record producer best known for his extensive work with Kings of Leon and contributions to modern rock and alternative music.
  • E. Tony Corrente
    Tony Corrente is an American football official best known for his long NFL refereeing career, including serving as the head referee for multiple high-profile games.
  • 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: Christopher Petrosino
Triple: [Starving, writer, Christopher Petrosino]
Generated description
Christopher Petrosino is a writer associated with the work "Starving."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Christopher Petrosino
Target entity description: Christopher Petrosino is a writer associated with the work "Starving."
  • A. John Ficarra
    John Ficarra is an American humor writer and longtime editor-in-chief of Mad magazine, known for shaping its satirical voice for decades.
  • B. Joe Venafro
    Joe Venafro is a television producer best known for serving as an executive producer on the reality law-enforcement series "Live PD."
  • C. Tony DeMarco
    Tony DeMarco was an American professional boxer and former world welterweight champion known for his aggressive, crowd-pleasing fighting style during the 1950s.
  • D. Angelo Petraglia
    Angelo Petraglia is an American songwriter and record producer best known for his extensive work with Kings of Leon and contributions to modern rock and alternative music.
  • E. Tony Corrente
    Tony Corrente is an American football official best known for his long NFL refereeing career, including serving as the head referee for multiple high-profile games.
  • 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_69d822e9b9e08190bedcc31a163fda82 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec817c39081909b08a0ffdfce9936 completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe9dbced588190ab7712c7ad50ee67 completed May 9, 2026, 2:36 a.m.
NEDg Description generation batch_69fe9e22453481909511619da9e319d5 completed May 9, 2026, 2:38 a.m.
NED2 Entity disambiguation (via description) batch_69fe9e610f788190bc33d8b8d7d718a2 completed May 9, 2026, 2:39 a.m.
Created at: April 10, 2026, 1:31 a.m.