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.