Triple
T10825123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Florence Mackenzie |
E255477
|
entity |
| Predicate | hasChild |
P369
|
FINISHED |
| Object |
Patricia Liddell
Patricia Liddell is the daughter of Australian wireless pioneer and radio engineer Florence Violet McKenzie.
|
E913735
|
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: Patricia Liddell | Statement: [Florence Mackenzie, hasChild, Patricia Liddell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Patricia Liddell Context triple: [Florence Mackenzie, hasChild, Patricia Liddell]
-
A.
Patricia Lovell
Patricia Lovell was an influential Australian film producer best known for championing landmark Australian cinema during the 1970s and 1980s.
-
B.
Patricia Tuckwell
Patricia Tuckwell was an Australian-born violinist and fashion model who became Countess of Harewood through her marriage to George Lascelles, 7th Earl of Harewood.
-
C.
Marjorie Parry
Marjorie Parry was the wife of renowned English conductor and cellist Sir John Barbirolli.
-
D.
Patricia Hodgson
Patricia Hodgson is a British media executive and regulator known for senior roles at the BBC and as chair of Ofcom.
-
E.
Marjorie Elizabeth Lloyd
Marjorie Elizabeth Lloyd is the daughter of famed silent film comedian and actor Harold Lloyd.
- 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: Patricia Liddell Triple: [Florence Mackenzie, hasChild, Patricia Liddell]
Generated description
Patricia Liddell is the daughter of Australian wireless pioneer and radio engineer Florence Violet McKenzie.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Patricia Liddell Target entity description: Patricia Liddell is the daughter of Australian wireless pioneer and radio engineer Florence Violet McKenzie.
-
A.
Patricia Lovell
Patricia Lovell was an influential Australian film producer best known for championing landmark Australian cinema during the 1970s and 1980s.
-
B.
Patricia Tuckwell
Patricia Tuckwell was an Australian-born violinist and fashion model who became Countess of Harewood through her marriage to George Lascelles, 7th Earl of Harewood.
-
C.
Marjorie Parry
Marjorie Parry was the wife of renowned English conductor and cellist Sir John Barbirolli.
-
D.
Patricia Hodgson
Patricia Hodgson is a British media executive and regulator known for senior roles at the BBC and as chair of Ofcom.
-
E.
Marjorie Elizabeth Lloyd
Marjorie Elizabeth Lloyd is the daughter of famed silent film comedian and actor Harold Lloyd.
- 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_69d6aa8081448190a9324184f2bd1c26 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d734d0389c819090a892693c4046ed |
completed | April 9, 2026, 5:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4cbce653481909b201a2d5871e129 |
completed | April 19, 2026, 12:34 p.m. |
| NEDg | Description generation | batch_69e4d9e87508819080932fac06fb754d |
completed | April 19, 2026, 1:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e4dda28b0081909245b65faae3533b |
completed | April 19, 2026, 1:50 p.m. |
Created at: April 8, 2026, 9:19 p.m.