Triple
T21976423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marius |
E542715
|
entity |
| Predicate | hasDirectorOccupation |
P141645
|
FINISHED |
| Object | actor |
—
|
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: actor | Statement: [Marius, hasDirectorOccupation, actor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasDirectorOccupation Context triple: [Marius, hasDirectorOccupation, actor]
-
A.
hasDirectorOfWork
Indicates that an entity has a specific person or organization serving as the director responsible for overseeing its work or project.
-
B.
mainProfessionOfDirector
chosen
Indicates the primary professional occupation or field in which a given director mainly works.
-
C.
hasDirectorStar
Indicates that a person both directed and starred in the same work (e.g., film, show, or production).
-
D.
hasDirectorInKeyWork
Indicates that a director is associated with a key or primary work of an entity (such as a film, series, or major production).
-
E.
directorOfWorkFeaturingSubject
Indicates that the subject is the director of a creative work in which another specified entity appears or is featured.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f124886418819091daed0988432350 |
completed | April 28, 2026, 9:20 p.m. |
| PD | Predicate disambiguation | batch_69e6f6154e408190acc5b2c278acaff4 |
completed | April 21, 2026, 3:59 a.m. |
Created at: April 16, 2026, 8:03 p.m.