Triple
T13277003
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Émile Reynaud |
E316215
|
entity |
| Predicate | typeOfAnimation |
P96809
|
FINISHED |
| Object | hand-painted images on flexible film bands |
—
|
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: hand-painted images on flexible film bands | Statement: [Émile Reynaud, typeOfAnimation, hand-painted images on flexible film bands]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfAnimation Context triple: [Émile Reynaud, typeOfAnimation, hand-painted images on flexible film bands]
-
A.
isAnimatedBy
Indicates that an entity’s motion or behavior is driven, controlled, or brought to life by another entity or process.
-
B.
featuresAnimation
chosen
Indicates that something includes or prominently presents an animation as part of its content or functionality.
-
C.
isAnimated
Indicates that an entity possesses animation, meaning it is depicted or realized through moving images rather than static or live-action form.
-
D.
movementType
Indicates the manner or mode in which an entity moves or is moved from one place or state to another.
-
E.
animator
Indicates that one entity serves as the animator or creator of animated content for another entity or work.
- 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_69d806b349908190a9a61dd9323bf153 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99cfdc9388190af1fdd3cd4717bd8 |
completed | April 11, 2026, 12:59 a.m. |
| PD | Predicate disambiguation | batch_69d98f6535688190a5a4549b7be2d611 |
completed | April 11, 2026, 12:01 a.m. |
Created at: April 9, 2026, 9:26 p.m.