Triple

T8947020
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth Olsen E213244 entity
Predicate spouse P13 FINISHED
Object Robbie Arnett
Robbie Arnett is an American musician best known as a member of the indie pop band Milo Greene and as the husband of actress Elizabeth Olsen.
E768402 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: Robbie Arnett | Statement: [Elizabeth Olsen, spouse, Robbie Arnett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robbie Arnett
Context triple: [Elizabeth Olsen, spouse, Robbie Arnett]
  • A. Jonny Moseley
    Jonny Moseley is an American freestyle skier best known for winning the gold medal in moguls and popularizing innovative tricks on the international stage.
  • B. Tim Rasmussen
    Tim Rasmussen is an American screenwriter best known for co-writing the romantic comedy film "License to Wed."
  • C. Neil Bonnett
    Neil Bonnett was an American NASCAR driver and member of the famed "Alabama Gang," known for his multiple Cup Series victories during the 1970s and 1980s.
  • D. Ricky Reed
    Ricky Reed is an American Grammy-winning record producer, songwriter, and musician known for his work with artists like Lizzo, Jason Derulo, and Twenty One Pilots.
  • E. Michael Thorpe
    Michael Thorpe is a relatively obscure individual whose specific public achievements or distinguishing characteristics are not widely documented.
  • 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: Robbie Arnett
Triple: [Elizabeth Olsen, spouse, Robbie Arnett]
Generated description
Robbie Arnett is an American musician best known as a member of the indie pop band Milo Greene and as the husband of actress Elizabeth Olsen.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Robbie Arnett
Target entity description: Robbie Arnett is an American musician best known as a member of the indie pop band Milo Greene and as the husband of actress Elizabeth Olsen.
  • A. Jonny Moseley
    Jonny Moseley is an American freestyle skier best known for winning the gold medal in moguls and popularizing innovative tricks on the international stage.
  • B. Tim Rasmussen
    Tim Rasmussen is an American screenwriter best known for co-writing the romantic comedy film "License to Wed."
  • C. Neil Bonnett
    Neil Bonnett was an American NASCAR driver and member of the famed "Alabama Gang," known for his multiple Cup Series victories during the 1970s and 1980s.
  • D. Ricky Reed
    Ricky Reed is an American Grammy-winning record producer, songwriter, and musician known for his work with artists like Lizzo, Jason Derulo, and Twenty One Pilots.
  • E. Michael Thorpe
    Michael Thorpe is a relatively obscure individual whose specific public achievements or distinguishing characteristics are not widely documented.
  • 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_69ca839843408190a39069a029a89f15 completed March 30, 2026, 2:07 p.m.
NER Named-entity recognition batch_69cc66deb8ec819087a9c5eddd24c08a completed April 1, 2026, 12:29 a.m.
NED1 Entity disambiguation (via context triple) batch_69cfc2022e30819089ba08f494a3a66f completed April 3, 2026, 1:34 p.m.
NEDg Description generation batch_69cfc27bae88819094bcfdf10e89018b completed April 3, 2026, 1:36 p.m.
NED2 Entity disambiguation (via description) batch_69cfc61d26fc8190817b430cb6fa9646 completed April 3, 2026, 1:52 p.m.
Created at: March 30, 2026, 6:59 p.m.