Triple
T19974137
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La Ciotat |
E493643
|
entity |
| Predicate | hasFilmHistoryEvent |
P2107
|
FINISHED |
| Object | screenings of early Lumière films |
—
|
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: screenings of early Lumière films | Statement: [La Ciotat, hasFilmHistoryEvent, screenings of early Lumière films]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasFilmHistoryEvent Context triple: [La Ciotat, hasFilmHistoryEvent, screenings of early Lumière films]
-
A.
hasPartInFilmHistory
Indicates that an entity has played a role or contributed in some way to the history or development of film.
-
B.
hasHistoricalEvent
chosen
Indicates that a historical event occurred in, is associated with, or is relevant to a particular entity.
-
C.
hasLiveActionFilm
Indicates that a subject has a corresponding live-action film adaptation or representation.
-
D.
filmHistory
Indicates that there is a historical or background connection between a film and another entity, such as its development, production, or past events related to it.
-
E.
hasNotablePersonEvent
Indicates that there exists a significant event in which the person plays a notable or central role.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65bcb72048190aedb4f085ace0493 |
completed | April 20, 2026, 5 p.m. |
| PD | Predicate disambiguation | batch_69e537fae79c81909eae39500766d0b6 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 11, 2026, 3:23 p.m.