Triple
T35709264
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Théâtre Optique |
E1031807
|
entity |
| Predicate | firstPublicScreeningsYearApprox |
P147226
|
FINISHED |
| Object | 1892 |
—
|
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: 1892 | Statement: [Théâtre Optique, firstPublicScreeningsYearApprox, 1892]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstPublicScreeningsYearApprox Context triple: [Théâtre Optique, firstPublicScreeningsYearApprox, 1892]
-
A.
firstShowYear
chosen
Indicates the year in which something (such as a show, event, or work) was first presented or made publicly available.
-
B.
firstStagedPremiereYear
Indicates the calendar year in which an entity’s first staged premiere or initial public performance took place.
-
C.
firstFilmScreenings
Indicates that the relationship links a film to the locations, venues, or events where it was first publicly screened.
-
D.
worldPremiereYear
Indicates the calendar year in which a work, event, or production was first publicly premiered anywhere in the world.
-
E.
yearOfFilmAppearance
Indicates the specific year in which a film appearance by an entity took place.
- 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_69f76e0df1d08190965b1c6dff94c391 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:05 p.m.