Triple
T5784809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Great Train Robbery |
E128243
|
entity |
| Predicate | editingTechnique |
P20443
|
FINISHED |
| Object | cross-cutting between parallel actions |
—
|
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: cross-cutting between parallel actions | Statement: [The Great Train Robbery, editingTechnique, cross-cutting between parallel actions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: editingTechnique Context triple: [The Great Train Robbery, editingTechnique, cross-cutting between parallel actions]
-
A.
editingMode
Indicates that an entity is currently in, or associated with, a state where its content or properties can be modified or edited.
-
B.
coEditor
Indicates that two or more entities share responsibility for editing the same work or publication.
-
C.
editedFilm
Indicates that one entity performed the film editing work on another entity, which is a film.
-
D.
modification
Indicates a change made to an existing entity, altering its properties, structure, or state from a prior version.
-
E.
editingStyle
chosen
Indicates the characteristic manner or approach used when revising, arranging, or refining content.
- 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_69c0084450048190bc647b649a05136b |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c02a19870c819084dc68b36b0cdd60 |
completed | March 22, 2026, 5:42 p.m. |
| PD | Predicate disambiguation | batch_69c021d2cd608190b98a7e3aa7001d27 |
completed | March 22, 2026, 5:07 p.m. |
Created at: March 22, 2026, 3:51 p.m.