Triple
T34727523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christmas on Earth Continued (related projects and screenings) |
E1001110
|
entity |
| Predicate | hasOriginalFilmYear |
P66420
|
FINISHED |
| Object | 1963 |
—
|
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: 1963 | Statement: [Christmas on Earth Continued (related projects and screenings), hasOriginalFilmYear, 1963]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOriginalFilmYear Context triple: [Christmas on Earth Continued (related projects and screenings), hasOriginalFilmYear, 1963]
-
A.
basedOnOriginalReleaseYear
Indicates that something is derived from, organized by, or determined according to the year in which the original version of a work was first released.
-
B.
workOriginalLanguagePublicationYear
Indicates the year in which the original-language version of a work was first published.
-
C.
notableOriginalFilm
Indicates that a work is the original film from which another work (such as a remake, adaptation, or related production) is derived or notably based.
-
D.
originallyPremieredInYear
chosen
Indicates the calendar year in which something (such as a work, show, or event) first premiered or was initially released.
-
E.
lastOriginalEditionYear
Indicates the calendar year in which the work’s most recent original (non-revised) edition was first published.
- 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_69f76daeb6e48190a4c9a6b0edc80f72 |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69fea2d0a4d08190aa06aeb902a02d5a |
completed | May 9, 2026, 2:58 a.m. |
| PD | Predicate disambiguation | batch_69fea24698348190b9b992a8e7cdbcd0 |
completed | May 9, 2026, 2:56 a.m. |
Created at: May 3, 2026, 3:59 p.m.