Triple
T28734998
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hush (2016 film) |
E730771
|
entity |
| Predicate | screenDebutOn |
P26909
|
FINISHED |
| Object | South by Southwest (SXSW) festival |
—
|
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: South by Southwest (SXSW) festival | Statement: [Hush (2016 film), screenDebutOn, South by Southwest (SXSW) festival]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: screenDebutOn Context triple: [Hush (2016 film), screenDebutOn, South by Southwest (SXSW) festival]
-
A.
screenDebut
chosen
Indicates the event or relationship in which an entity appears on screen for the first time in a film, television, or other visual media production.
-
B.
screenDebutWithA24
Indicates that an entity made its first on-screen appearance in a production distributed or produced by A24.
-
C.
screenDebutTypeFor
Indicates the type or category of screen debut associated with a given entity (e.g., a person or work).
-
D.
screensAt
Indicates that one entity shows, projects, or displays another entity (such as a film, program, or content) on a screen or at a screening venue.
-
E.
screenDebutAsWriterFor
Indicates that an individual made their first credited screenwriting appearance in a particular film, show, or screen production.
- 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_69f043eae0908190b28ce314686247d7 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f6645ba71c81908044ade6ab577018 |
completed | May 2, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f663362c008190a22afed262f1e426 |
completed | May 2, 2026, 8:48 p.m. |
Created at: April 28, 2026, 6 a.m.