Triple

T5913973
Position Surface form Disambiguated ID Type / Status
Subject American Pie E131532 entity
Predicate producer P490 FINISHED
Object Craig Perry
Craig Perry is a film producer best known for his work on the hit teen comedy franchise "American Pie."
E556133 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: Craig Perry | Statement: [American Pie, producer, Craig Perry]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Craig Perry
Context triple: [American Pie, producer, Craig Perry]
  • A. Philip Perry
    Philip Perry is an American attorney and former Department of Homeland Security general counsel, known for his work in government and as the husband of politician Liz Cheney.
  • B. Anthony Perry
    Anthony Perry is a film producer best known for his work on the World War II drama "Operation Daybreak."
  • C. Peter Perry
    Peter Perry was a prominent 19th-century Canadian reform politician who emerged as a leading figure of the Clear Grits movement in Upper Canada.
  • D. Michael R. Perry
    Michael R. Perry is an American screenwriter and producer known for his work in film and television, including contributions to genre projects such as the dark comedy horror film "The Voices."
  • E. Perry Johanson
    Perry Johanson was an American architect best known as one of the founding partners of the global architecture and design firm NBBJ.
  • 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: Craig Perry
Triple: [American Pie, producer, Craig Perry]
Generated description
Craig Perry is a film producer best known for his work on the hit teen comedy franchise "American Pie."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Craig Perry
Target entity description: Craig Perry is a film producer best known for his work on the hit teen comedy franchise "American Pie."
  • A. Philip Perry
    Philip Perry is an American attorney and former Department of Homeland Security general counsel, known for his work in government and as the husband of politician Liz Cheney.
  • B. Anthony Perry
    Anthony Perry is a film producer best known for his work on the World War II drama "Operation Daybreak."
  • C. Peter Perry
    Peter Perry was a prominent 19th-century Canadian reform politician who emerged as a leading figure of the Clear Grits movement in Upper Canada.
  • D. Michael R. Perry
    Michael R. Perry is an American screenwriter and producer known for his work in film and television, including contributions to genre projects such as the dark comedy horror film "The Voices."
  • E. Perry Johanson
    Perry Johanson was an American architect best known as one of the founding partners of the global architecture and design firm NBBJ.
  • 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_69c008593a44819081a07ae0efe6c574 completed March 22, 2026, 3:18 p.m.
NER Named-entity recognition batch_69c037b9f0908190ad854e5f2600f114 completed March 22, 2026, 6:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0c01ddd30819088571c5b56dbae83 completed March 23, 2026, 4:22 a.m.
NEDg Description generation batch_69c0c214d8988190a599d2b65072524f completed March 23, 2026, 4:31 a.m.
NED2 Entity disambiguation (via description) batch_69c0c30ef6c88190bb4afa41ae8f6a20 completed March 23, 2026, 4:35 a.m.
Created at: March 22, 2026, 3:59 p.m.