Triple

T5944303
Position Surface form Disambiguated ID Type / Status
Subject Tina Sinatra E132240 entity
Predicate spouse P13 FINISHED
Object Wes Farrell
Wes Farrell was an American songwriter and record producer best known for co-writing numerous pop hits in the 1960s and 1970s, including “Hang On Sloopy.”
 E559542 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: Wes Farrell | Statement: [Tina Sinatra, spouse, Wes Farrell]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Wes Farrell
Context triple: [Tina Sinatra, spouse, Wes Farrell]
  • A. Chris MacFarland
    Chris MacFarland is an NHL executive who serves as the general manager of the Colorado Avalanche, overseeing the team's hockey operations and roster decisions.
  • B. Nate Farley
    Nate Farley is an American rock guitarist best known for his work in the indie and alternative scenes, including his tenure with The Breeders.
  • C. Oakes Fegley
    Oakes Fegley is an American actor best known for his leading roles as a child and teen in films such as "Pete's Dragon" and "The Goldfinch."
  • D. Matt Wolpert
    Matt Wolpert is a television writer and producer best known for co-creating the alternate-history space drama series "For All Mankind."
  • E. Justin Wilkes
    Justin Wilkes is a television producer and creator known for developing the series "Mars" and other documentary and scripted projects.
  • 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: Wes Farrell
Triple: [Tina Sinatra, spouse, Wes Farrell]
Generated description
Wes Farrell was an American songwriter and record producer best known for co-writing numerous pop hits in the 1960s and 1970s, including “Hang On Sloopy.”
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Wes Farrell
Target entity description: Wes Farrell was an American songwriter and record producer best known for co-writing numerous pop hits in the 1960s and 1970s, including “Hang On Sloopy.”
  • A. Chris MacFarland
    Chris MacFarland is an NHL executive who serves as the general manager of the Colorado Avalanche, overseeing the team's hockey operations and roster decisions.
  • B. Nate Farley
    Nate Farley is an American rock guitarist best known for his work in the indie and alternative scenes, including his tenure with The Breeders.
  • C. Oakes Fegley
    Oakes Fegley is an American actor best known for his leading roles as a child and teen in films such as "Pete's Dragon" and "The Goldfinch."
  • D. Matt Wolpert
    Matt Wolpert is a television writer and producer best known for co-creating the alternate-history space drama series "For All Mankind."
  • E. Justin Wilkes
    Justin Wilkes is a television producer and creator known for developing the series "Mars" and other documentary and scripted projects.
  • 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_69c00869d3308190af89b2453e0f7546 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c03937b4a88190819a1fd63fc3d3ed completed March 22, 2026, 6:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c0e3bd196081908361a38ca17309c6 completed March 23, 2026, 6:54 a.m.
NEDg Description generation batch_69c0f87d34f88190ad3a91b64079b213 completed March 23, 2026, 8:23 a.m.
NED2 Entity disambiguation (via description) batch_69c0f9aabd6c8190bcb2a2022a00672d completed March 23, 2026, 8:28 a.m.
Created at: March 22, 2026, 4:01 p.m.