Triple
T34392632
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbara Novak |
E882745
|
entity |
| Predicate | workPublishedInFiction |
P106268
|
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, workPublishedInFiction, Down with Love (book within the film)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: workPublishedInFiction Context triple: [Barbara Novak, workPublishedInFiction, Down with Love (book within the film)]
-
A.
workInFiction
Indicates that one entity is a fictional work in which the other entity appears or is set.
-
B.
hasAssociatedWorkOfFiction
chosen
Indicates that an entity is linked to a related work of fiction, such as a novel, film, or story that is associated with it.
-
C.
worksWithInFiction
Indicates that two fictional characters are depicted as collaborating, interacting, or being associated with each other within a narrative work.
-
D.
workPublishedAuthor
Indicates that a particular work was created and published by a specific author.
-
E.
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.
- 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_69f349c1304081909331872829e38106 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f71c35327c8190884f1bfe12bd2cd7 |
completed | May 3, 2026, 9:58 a.m. |
| PD | Predicate disambiguation | batch_69f71822d0e88190ac9731c7ae5a4def |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 1:59 a.m.