Triple
T26393282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Custody (2017 film) |
E663474
|
entity |
| Predicate | shortFilmPrequel |
P63467
|
FINISHED |
| Object | Just Before Losing Everything |
—
|
NE NERFINISHED |
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: Just Before Losing Everything | Statement: [Custody (2017 film), shortFilmPrequel, Just Before Losing Everything]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shortFilmPrequel Context triple: [Custody (2017 film), shortFilmPrequel, Just Before Losing Everything]
-
A.
hasShortFilmPrecursor
chosen
Indicates that a work is preceded by a short film that serves as an earlier or foundational version of it.
-
B.
isPrequelTo
Indicates that one work or event occurs earlier in time and narratively sets up or leads into another work or event.
-
C.
prequelOrSequelTo
Indicates that one work in a narrative series occurs earlier or later in the storyline or release order relative to another work, as its prequel or sequel.
-
D.
shortFilmComponent
Indicates that one entity is a component, segment, or part of a short film represented by the other entity.
-
E.
precedesInFilm
Indicates that one film is released or occurs earlier in sequence or narrative order than another film.
- 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_69ee883823988190b418b111be28a44a |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f610c0ed7c81908058c49aa53e03a6 |
completed | May 2, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f60b89cc048190a9feb24466006be0 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 26, 2026, 11:27 p.m.