Triple
T34392673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbara Novak |
E882747
|
entity |
| Predicate | workPublishedInStory |
P179381
|
FINISHED |
| Object | Down with Love (book within the film) |
—
|
NE NERFINISHED |
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: Down with Love (book within the film) | Statement: [Barbara Novak, workPublishedInStory, Down with Love (book within the film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workPublishedInStory Context triple: [Barbara Novak, workPublishedInStory, Down with Love (book within the film)]
-
A.
workPublishedAuthor
Indicates that a particular work was created and published by a specific author.
-
B.
workPublishedBy
Indicates that a work (such as a book, article, or other creation) has been issued or made publicly available by a particular publisher or publishing entity.
-
C.
workPublishedUnderName
Indicates that a work was released or made public using a specific name (such as a real name, pseudonym, or organizational name) as the credited author or source.
-
D.
createdInWorkPublishedIn
Indicates that something was created within a work that was subsequently published in a particular publication or venue.
-
E.
selfPublished
Indicates that an entity has published its own work independently, without an external publisher.
- F. None of above. chosen
Provenance (4 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_69f349c1304081909331872829e38106 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f720cc1bfc8190a16118e3af8e9316 |
completed | May 3, 2026, 10:17 a.m. |
| PD | Predicate disambiguation | batch_69f71cc6397881909aaad37a9daa8a7e |
completed | May 3, 2026, 10 a.m. |
| PDg | Predicate description generation | batch_69f71fb0172c81908f23e95ff16b0dec |
completed | May 3, 2026, 10:13 a.m. |
Created at: May 1, 2026, 1:59 a.m.