Triple

T3379373
Position Surface form Disambiguated ID Type / Status
Subject Mark O'Brien E71143 entity
Predicate spouse P13 FINISHED
Object Georgina Reilly
Georgina Reilly is a Canadian actress known for her roles in television series such as "Republic of Doyle" and "Murdoch Mysteries."
E352428 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: Georgina Reilly | Statement: [Mark O'Brien, spouse, Georgina Reilly]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Georgina Reilly
Context triple: [Mark O'Brien, spouse, Georgina Reilly]
  • A. Carreen O'Hara
    Carreen O'Hara is a gentle, devout younger sister of Scarlett O'Hara in Margaret Mitchell's novel "Gone with the Wind."
  • B. Elizabeth French
    Elizabeth French was the wife of John Tillotson, the 17th-century Archbishop of Canterbury.
  • C. Vivien
    Vivien is a famous Pre-Raphaelite painting by Frederic Sandys depicting the Arthurian enchantress often associated with Merlin.
  • D. Letitia Cropley
    Letitia Cropley is an eccentric parishioner in the British sitcom "The Vicar of Dibley," best known for her bizarre and unappetizing culinary creations.
  • E. Marie Morgan
    Marie Morgan is a central female character in Ernest Hemingway’s novel and its film adaptation "To Have and Have Not," often depicted as a tough, resourceful, and romantically involved companion to the protagonist.
  • 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: Georgina Reilly
Triple: [Mark O'Brien, spouse, Georgina Reilly]
Generated description
Georgina Reilly is a Canadian actress known for her roles in television series such as "Republic of Doyle" and "Murdoch Mysteries."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Georgina Reilly
Target entity description: Georgina Reilly is a Canadian actress known for her roles in television series such as "Republic of Doyle" and "Murdoch Mysteries."
  • A. Carreen O'Hara
    Carreen O'Hara is a gentle, devout younger sister of Scarlett O'Hara in Margaret Mitchell's novel "Gone with the Wind."
  • B. Elizabeth French
    Elizabeth French was the wife of John Tillotson, the 17th-century Archbishop of Canterbury.
  • C. Vivien
    Vivien is a famous Pre-Raphaelite painting by Frederic Sandys depicting the Arthurian enchantress often associated with Merlin.
  • D. Letitia Cropley
    Letitia Cropley is an eccentric parishioner in the British sitcom "The Vicar of Dibley," best known for her bizarre and unappetizing culinary creations.
  • E. Marie Morgan
    Marie Morgan is a central female character in Ernest Hemingway’s novel and its film adaptation "To Have and Have Not," often depicted as a tough, resourceful, and romantically involved companion to the protagonist.
  • 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_69ad85a7f80c8190a05e43013f298942 completed March 8, 2026, 2:20 p.m.
NER Named-entity recognition batch_69adb2ec38d88190be8c824daeca5ab6 completed March 8, 2026, 5:33 p.m.
NED1 Entity disambiguation (via context triple) batch_69b3344c0698819082d856d8be7f2c18 completed March 12, 2026, 9:46 p.m.
NEDg Description generation batch_69b334e661ac8190b8ff974c9568caf8 completed March 12, 2026, 9:49 p.m.
NED2 Entity disambiguation (via description) batch_69b3354fe7748190a0324551d1a8bc1b completed March 12, 2026, 9:51 p.m.
Created at: March 8, 2026, 3:14 p.m.