Triple
T12115649
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael (Love Actually) |
E288551
|
entity |
| Predicate | worksAsDoubleFor |
P103368
|
FINISHED |
| Object | fictional film actors in Love Actually |
—
|
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: fictional film actors in Love Actually | Statement: [Michael (Love Actually), worksAsDoubleFor, fictional film actors in Love Actually]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worksAsDoubleFor Context triple: [Michael (Love Actually), worksAsDoubleFor, fictional film actors in Love Actually]
-
A.
worksAs
Indicates that an entity performs the role, job, or occupation specified by another entity.
-
B.
worksThrough
Indicates that one entity performs an action, causes an effect, or achieves a result by using, employing, or acting via another entity as an intermediary or means.
-
C.
worksFor
Indicates that one entity is employed by or performs work on behalf of another entity, typically an organization or individual.
-
D.
worksWhen
Indicates that one entity functions or operates correctly only under the conditions or context defined by another entity.
-
E.
hasDouble
Indicates that an entity possesses or is associated with a counterpart that is a duplicate or closely similar version of it.
- 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_69d6ab4a5c448190a110d1273314b21a |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d9164ada5081908676bd9e5947268a |
completed | April 10, 2026, 3:24 p.m. |
| PD | Predicate disambiguation | batch_69d9150497408190921334d21503375a |
completed | April 10, 2026, 3:19 p.m. |
| PDg | Predicate description generation | batch_69d916481a008190ae66677b9e6dd961 |
completed | April 10, 2026, 3:24 p.m. |
Created at: April 8, 2026, 9:49 p.m.