Triple
T20928570
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Diary of a Bad Year |
E515407
|
entity |
| Predicate | authorNationalityAtPublication |
P6689
|
FINISHED |
| Object | Australian |
—
|
LITERAL FINISHED |
How this triple was built (2 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: Australian | Statement: [Diary of a Bad Year, authorNationalityAtPublication, Australian]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: authorNationalityAtPublication Context triple: [Diary of a Bad Year, authorNationalityAtPublication, Australian]
-
A.
authorNationality
chosen
Indicates the relationship between an author and the country or nationality with which that author is identified.
-
B.
creatorNationality
Indicates that the creator of an entity has a specified national affiliation or citizenship.
-
C.
coAuthorNationality
Indicates that two or more co-authors of a work share the same nationality or have nationalities being related in the context of their co-authorship.
-
D.
appearsInWorkByAuthorNationality
Indicates that an entity appears in a work created by an author of a specified nationality.
-
E.
creatorEthnicityOfAuthor
Indicates that the specified ethnicity is attributed to the creator who is the author of the referenced work or entity.
- F. None of above.
Provenance (3 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_69e0b4fb431c8190b9d40e6a72f0cc87 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6f653a25c8190adb46f5d764afba7 |
completed | April 21, 2026, 4 a.m. |
| PD | Predicate disambiguation | batch_69e5c9af1fe08190953366a466950140 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:49 p.m.