Triple

T19527018
Position Surface form Disambiguated ID Type / Status
Subject Joe Sawyer E488545 entity
Predicate spouse P13 FINISHED
Object June Almy
June Almy was the wife of Canadian-born character actor Joe Sawyer, known for his prolific work in American film and television during the mid-20th century.
E1425215 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: June Almy | Statement: [Joe Sawyer, spouse, June Almy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: June Almy
Context triple: [Joe Sawyer, spouse, June Almy]
  • A. Alma Ross
    Alma Ross was one of the early wives of famed American jazz and swing musician Louis Prima.
  • B. Marie Allen
    Marie Allen is the naive young woman whose harrowing transformation behind bars drives the narrative of the classic women-in-prison film "Caged."
  • C. Mayme Kelso
    Mayme Kelso was an American actress of the silent film era, known for her character roles in early 20th-century cinema.
  • D. Marie Alweather
    Marie Alweather is a character from the animated film "Paulie," appearing as part of the story surrounding the talking parrot's adventures.
  • E. Alyce Mayo
    Alyce Mayo is an American actress and former wife of acclaimed actor Peter Falk.
  • 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: June Almy
Triple: [Joe Sawyer, spouse, June Almy]
Generated description
June Almy was the wife of Canadian-born character actor Joe Sawyer, known for his prolific work in American film and television during the mid-20th century.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: June Almy
Target entity description: June Almy was the wife of Canadian-born character actor Joe Sawyer, known for his prolific work in American film and television during the mid-20th century.
  • A. Alma Ross
    Alma Ross was one of the early wives of famed American jazz and swing musician Louis Prima.
  • B. Marie Allen
    Marie Allen is the naive young woman whose harrowing transformation behind bars drives the narrative of the classic women-in-prison film "Caged."
  • C. Mayme Kelso
    Mayme Kelso was an American actress of the silent film era, known for her character roles in early 20th-century cinema.
  • D. Marie Alweather
    Marie Alweather is a character from the animated film "Paulie," appearing as part of the story surrounding the talking parrot's adventures.
  • E. Alyce Mayo
    Alyce Mayo is an American actress and former wife of acclaimed actor Peter Falk.
  • 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_69d8e8da8bec819081f400199491ccc3 completed April 10, 2026, 12:11 p.m.
NER Named-entity recognition batch_69e6363c2660819093a6b9a444ca0ad4 completed April 20, 2026, 2:20 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08693a75d08190b5e760695e35f19d completed May 16, 2026, 12:55 p.m.
NEDg Description generation batch_6a086a1483048190b1a5176d12ed1a98 completed May 16, 2026, 12:59 p.m.
NED2 Entity disambiguation (via description) batch_6a086b0e34ac8190b544b2a78f776d5d completed May 16, 2026, 1:03 p.m.
Created at: April 10, 2026, 1:41 p.m.