Triple
T32588403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les Films Jean Epstein |
E832990
|
entity |
| Predicate | producedWorksInMedium |
P87617
|
FINISHED |
| Object | silent film |
—
|
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: silent film | Statement: [Les Films Jean Epstein, producedWorksInMedium, silent film]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: producedWorksInMedium Context triple: [Les Films Jean Epstein, producedWorksInMedium, silent film]
-
A.
workProducedBy
Indicates that a particular work (such as a creation, product, or result) was created, generated, or authored by a specific agent or entity.
-
B.
genreOfProducedWorks
chosen
Indicates that one entity is the genre category to which the works produced by another entity belong.
-
C.
producedFilm
Indicates that one entity served as the producer (or production company) responsible for making or financing the creation of a particular film.
-
D.
workedAsProducerFor
Indicates that one entity served in the role of producer for a work, project, or production associated with another entity.
-
E.
worksCollectedBy
Indicates that one entity gathers, compiles, or curates the works (such as creations, publications, or outputs) produced by another 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_69f34929ff648190aded9424aa7564ae |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fde5d7d9548190880a9d95b8f0f66b |
completed | May 8, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69fde4e1bf9c81909754545275eccc03 |
completed | May 8, 2026, 1:28 p.m. |
Created at: May 1, 2026, 1:04 a.m.