Triple

T20212396
Position Surface form Disambiguated ID Type / Status
Subject Bill Oddie E493519 entity
Predicate spouse P13 FINISHED
Object Laura Beaumont
Laura Beaumont is a British writer and television producer best known for her work in comedy and children’s programming.
E1418418 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: Laura Beaumont | Statement: [Bill Oddie, spouse, Laura Beaumont]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Laura Beaumont
Context triple: [Bill Oddie, spouse, Laura Beaumont]
  • A. Garcelle Beauvais
    Garcelle Beauvais is a Haitian-American actress, television personality, and former fashion model known for roles in series like NYPD Blue and The Real Housewives of Beverly Hills.
  • B. Emily Deschanel
    Emily Deschanel is an American actress best known for starring as Dr. Temperance "Bones" Brennan on the long-running television series "Bones."
  • C. Sarah Baldwin
    Sarah Baldwin is an actress known for appearing in the romantic comedy film "Something Borrowed."
  • D. George Newbern
    George Newbern is an American actor best known for his roles in films like "Father of the Bride" and for voicing Superman in various animated DC Comics projects.
  • E. Elizabeth Gilliland
    Elizabeth Gilliland was a woman after whom the town of Elizabethtown in New York was named, likely an early settler or figure of local historical significance.
  • 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: Laura Beaumont
Triple: [Bill Oddie, spouse, Laura Beaumont]
Generated description
Laura Beaumont is a British writer and television producer best known for her work in comedy and children’s programming.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Laura Beaumont
Target entity description: Laura Beaumont is a British writer and television producer best known for her work in comedy and children’s programming.
  • A. Garcelle Beauvais
    Garcelle Beauvais is a Haitian-American actress, television personality, and former fashion model known for roles in series like NYPD Blue and The Real Housewives of Beverly Hills.
  • B. Emily Deschanel
    Emily Deschanel is an American actress best known for starring as Dr. Temperance "Bones" Brennan on the long-running television series "Bones."
  • C. Sarah Baldwin
    Sarah Baldwin is an actress known for appearing in the romantic comedy film "Something Borrowed."
  • D. George Newbern
    George Newbern is an American actor best known for his roles in films like "Father of the Bride" and for voicing Superman in various animated DC Comics projects.
  • E. Elizabeth Gilliland
    Elizabeth Gilliland was a woman after whom the town of Elizabethtown in New York was named, likely an early settler or figure of local historical significance.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66ed627f48190a8ba638b85977af3 completed April 20, 2026, 6:22 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0843f2768c8190b54054fc00c84332 completed May 16, 2026, 10:16 a.m.
NEDg Description generation batch_6a0844fdbc888190bd3a9e02d5f9bcc2 completed May 16, 2026, 10:20 a.m.
NED2 Entity disambiguation (via description) batch_6a0845e241048190ba7fb657d4dca3d7 completed May 16, 2026, 10:24 a.m.
Created at: April 11, 2026, 11:38 p.m.