Triple

T17798217
Position Surface form Disambiguated ID Type / Status
Subject Salem E444348 entity
Predicate castMember P1668 FINISHED
Object Joe Doyle
Joe Doyle is an actor best known for his role in the supernatural horror television series "Salem."
E1365277 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: Joe Doyle | Statement: [Salem, castMember, Joe Doyle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joe Doyle
Context triple: [Salem, castMember, Joe Doyle]
  • A. Jake Doyle
    Jake Doyle is the wisecracking private investigator protagonist of the Canadian television series "Republic of Doyle," set in St. John’s, Newfoundland.
  • B. Kevin Doyle
    Kevin Doyle is the witty, secretly romantic journalist and love interest of Katherine Heigl’s character in the romantic comedy film "27 Dresses."
  • C. Kevin Doyle
    Kevin Doyle is a British actor best known for his role as Joseph Molesley in the television series "Downton Abbey."
  • D. Ray Doolan
    Ray Doolan is an Australian local government official who serves as the mayor of Carrathool Shire in New South Wales.
  • E. Sam Donnelly
    Sam Donnelly is a television producer best known for serving as an executive producer on the popular talent competition show "America's Got Talent."
  • 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: Joe Doyle
Triple: [Salem, castMember, Joe Doyle]
Generated description
Joe Doyle is an actor best known for his role in the supernatural horror television series "Salem."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Joe Doyle
Target entity description: Joe Doyle is an actor best known for his role in the supernatural horror television series "Salem."
  • A. Jake Doyle
    Jake Doyle is the wisecracking private investigator protagonist of the Canadian television series "Republic of Doyle," set in St. John’s, Newfoundland.
  • B. Kevin Doyle
    Kevin Doyle is the witty, secretly romantic journalist and love interest of Katherine Heigl’s character in the romantic comedy film "27 Dresses."
  • C. Kevin Doyle
    Kevin Doyle is a British actor best known for his role as Joseph Molesley in the television series "Downton Abbey."
  • D. Ray Doolan
    Ray Doolan is an Australian local government official who serves as the mayor of Carrathool Shire in New South Wales.
  • E. Sam Donnelly
    Sam Donnelly is a television producer best known for serving as an executive producer on the popular talent competition show "America's Got Talent."
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e487fcfdc8819086f41152860dfe18 completed April 19, 2026, 7:45 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0700c58c008190be11ddd0c0d13595 completed May 15, 2026, 11:17 a.m.
NEDg Description generation batch_6a07026b3cd08190b595dd7c724ff5e0 completed May 15, 2026, 11:24 a.m.
NED2 Entity disambiguation (via description) batch_6a0702f869f0819090aec0c308b0d888 completed May 15, 2026, 11:26 a.m.
Created at: April 10, 2026, 10:13 a.m.