Triple
T2350779
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 28 Days Later |
E47441
|
entity |
| Predicate | filmRatingUK |
P3533
|
FINISHED |
| Object | 18 |
—
|
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: 18 | Statement: [28 Days Later, filmRatingUK, 18]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: filmRatingUK Context triple: [28 Days Later, filmRatingUK, 18]
-
A.
bbfcRatingUK
chosen
Indicates the film or media content rating assigned by the British Board of Film Classification (BBFC) in the United Kingdom.
-
B.
TVRatingUS
Indicates the television content rating assigned to a program under the U.S. TV parental guidelines system.
-
C.
USRating
Indicates that an entity has been assigned a rating, classification, or evaluation according to a United States–based standard or system.
-
D.
mpaaRating
Indicates the official Motion Picture Association of America (MPAA) content rating assigned to a film or audiovisual work.
-
E.
hasFilmRatingAustralia
Indicates that an entity (typically a film or audiovisual work) has a specific official classification or rating assigned by the Australian film rating system.
- 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_69a88a1b678c8190bce986922ba60ce0 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abcb802da08190980100444010f91e |
completed | March 7, 2026, 6:53 a.m. |
| PD | Predicate disambiguation | batch_69abc5981ce48190a3f7852d28276e11 |
completed | March 7, 2026, 6:28 a.m. |
Created at: March 4, 2026, 7:54 p.m.