Triple

T6957488
Position Surface form Disambiguated ID Type / Status
Subject Dustin Henderson E161281 entity
Predicate romanticInterest P7325 FINISHED
Object Suzie
Suzie is a brilliant, tech-savvy girl from Stranger Things who helps Dustin Henderson and his friends by providing crucial scientific and hacking assistance.
 E633927 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: Suzie | Statement: [Dustin Henderson, romanticInterest, Suzie]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Suzie
Context triple: [Dustin Henderson, romanticInterest, Suzie]
  • A. Suze
    The Suze is a river in western Switzerland that flows through the Jura region and the city of Biel/Bienne before emptying into Lake Biel.
  • B. Suze
    Suze is the nickname of Suze Rotolo, an American artist and political activist best known for her relationship with Bob Dylan in the early 1960s.
  • C. Suzanne
    "Suzanne" is a renowned song by Leonard Cohen, celebrated for its poetic lyrics and haunting melody.
  • D. Suzanne
    Suzanne is a central character in Steve Martin’s play "Picasso at the Lapin Agile," representing a young woman entangled romantically with both Picasso and other men in the bohemian Parisian setting.
  • E. Sue
    Sue is the given name of Sue Storm, the Invisible Woman and a central member of Marvel’s superhero team the Fantastic Four.
  • 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: Suzie
Triple: [Dustin Henderson, romanticInterest, Suzie]
Generated description
Suzie is a brilliant, tech-savvy girl from Stranger Things who helps Dustin Henderson and his friends by providing crucial scientific and hacking assistance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Suzie
Target entity description: Suzie is a brilliant, tech-savvy girl from Stranger Things who helps Dustin Henderson and his friends by providing crucial scientific and hacking assistance.
  • A. Suze
    Suze is the nickname of Suze Rotolo, an American artist and political activist best known for her relationship with Bob Dylan in the early 1960s.
  • B. Suze
    The Suze is a river in western Switzerland that flows through the Jura region and the city of Biel/Bienne before emptying into Lake Biel.
  • C. Suzanne
    "Suzanne" is a renowned song by Leonard Cohen, celebrated for its poetic lyrics and haunting melody.
  • D. Suzanne
    Suzanne is a central character in Steve Martin’s play "Picasso at the Lapin Agile," representing a young woman entangled romantically with both Picasso and other men in the bohemian Parisian setting.
  • E. Sue
    Sue is the given name of Sue Storm, the Invisible Woman and a central member of Marvel’s superhero team the Fantastic Four.
  • 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_69c68852a9a0819097797e31d492e273 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dad0e52081908b524dc6a66bab01 completed March 27, 2026, 7:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7618df8648190bec6c0aaca312efd completed March 28, 2026, 5:05 a.m.
NEDg Description generation batch_69c763e95d8081908885dec9a5ca90c7 completed March 28, 2026, 5:15 a.m.
NED2 Entity disambiguation (via description) batch_69c7643fdea0819093205e5d8bf9a818 completed March 28, 2026, 5:16 a.m.
Created at: March 27, 2026, 2:29 p.m.