Triple
T20946853
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Maxwell Coetzee |
E515863
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Philippa Jubber
Philippa Jubber is the former wife of Nobel Prize–winning South African novelist J. M. Coetzee.
|
E1471598
|
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: Philippa Jubber | Statement: [John Maxwell Coetzee, spouse, Philippa Jubber]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Philippa Jubber Context triple: [John Maxwell Coetzee, spouse, Philippa Jubber]
-
A.
Philippa Goslett
Philippa Goslett is a British screenwriter and producer known for her work on films such as the biblical drama "Mary Magdalene" (2018).
-
B.
Philippa Price
Philippa Price is a British visual artist and director known for her surreal, high-concept music videos and fashion films for major pop and R&B artists.
-
C.
Philippa Perry
Philippa Perry is a British psychotherapist and author known for her accessible books and media work on psychology, relationships, and mental health.
-
D.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
E.
Gillian Juckes
Gillian Juckes is a writer known for her work associated with the Care organization.
- 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: Philippa Jubber Triple: [John Maxwell Coetzee, spouse, Philippa Jubber]
Generated description
Philippa Jubber is the former wife of Nobel Prize–winning South African novelist J. M. Coetzee.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Philippa Jubber Target entity description: Philippa Jubber is the former wife of Nobel Prize–winning South African novelist J. M. Coetzee.
-
A.
Philippa Goslett
Philippa Goslett is a British screenwriter and producer known for her work on films such as the biblical drama "Mary Magdalene" (2018).
-
B.
Philippa Price
Philippa Price is a British visual artist and director known for her surreal, high-concept music videos and fashion films for major pop and R&B artists.
-
C.
Philippa Perry
Philippa Perry is a British psychotherapist and author known for her accessible books and media work on psychology, relationships, and mental health.
-
D.
Philippa Giles
Philippa Giles is a British television producer best known for her work on acclaimed drama series such as Luther.
-
E.
Gillian Juckes
Gillian Juckes is a writer known for her work associated with the Care organization.
- 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_69e0b4fcd678819087a304291f14330a |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fad97aa48190b4be692e3afce8c9 |
completed | April 21, 2026, 4:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a097eb4d62881908c21b7d0b6441e22 |
completed | May 17, 2026, 8:39 a.m. |
| NEDg | Description generation | batch_6a0980572ce08190b873e880cd775bdf |
completed | May 17, 2026, 8:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0980bbd6e081909568ce48d735ae41 |
completed | May 17, 2026, 8:47 a.m. |
Created at: April 16, 2026, 12:56 p.m.