Triple

T3205087
Position Surface form Disambiguated ID Type / Status
Subject Diff'rent Strokes E67141 entity
Predicate portrayedBy P1507 FINISHED
Object Todd Bridges
Todd Bridges is an American actor best known for playing Willis Jackson on the sitcom "Diff'rent Strokes."
E335272 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: Todd Bridges | Statement: [Diff'rent Strokes, portrayedBy, Todd Bridges]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Todd Bridges
Context triple: [Diff'rent Strokes, portrayedBy, Todd Bridges]
  • A. Jake Scott
    Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
  • B. Jake Scott
    Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
  • C. Christian Broun
    Christian Broun was a Scottish noblewoman best known as the mother of James Broun-Ramsay, 1st Marquess of Dalhousie, who served as Governor-General of India in the mid-19th century.
  • D. Tom Love
    Tom Love is an American computer scientist and software engineer best known as a co-creator of the Objective-C programming language.
  • E. Tom Cross
    Tom Cross is an Academy Award–winning American film editor known for his work on acclaimed movies such as "Whiplash" and "La La Land."
  • 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: Todd Bridges
Triple: [Diff'rent Strokes, portrayedBy, Todd Bridges]
Generated description
Todd Bridges is an American actor best known for playing Willis Jackson on the sitcom "Diff'rent Strokes."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Todd Bridges
Target entity description: Todd Bridges is an American actor best known for playing Willis Jackson on the sitcom "Diff'rent Strokes."
  • A. Jake Scott
    Jake Scott was an American NFL safety best known for his standout play with the Miami Dolphins in the early 1970s, including their perfect season.
  • B. Jake Scott
    Jake Scott is a British film and music video director known for his work with prominent rock bands and artists.
  • C. Christian Broun
    Christian Broun was a Scottish noblewoman best known as the mother of James Broun-Ramsay, 1st Marquess of Dalhousie, who served as Governor-General of India in the mid-19th century.
  • D. Tom Love
    Tom Love is an American computer scientist and software engineer best known as a co-creator of the Objective-C programming language.
  • E. Tom Cross
    Tom Cross is an Academy Award–winning American film editor known for his work on acclaimed movies such as "Whiplash" and "La La Land."
  • 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_69ad8589bd988190afa7ed2bdffb7b33 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaa559848819082d1e61f586278dd completed March 8, 2026, 4:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69b24bcbb0e88190b4413c4ba3de0eeb completed March 12, 2026, 5:14 a.m.
NEDg Description generation batch_69b24ca05434819080ee515b1e7bdcb4 completed March 12, 2026, 5:18 a.m.
NED2 Entity disambiguation (via description) batch_69b24d19250c81908a9c3ac95b83a473 completed March 12, 2026, 5:20 a.m.
Created at: March 8, 2026, 3:07 p.m.