Triple
T8539117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lunar: Eternal Blue |
E202150
|
entity |
| Predicate | hasCutscenes |
P83202
|
FINISHED |
| Object | full-motion video cutscenes |
—
|
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: full-motion video cutscenes | Statement: [Lunar: Eternal Blue, hasCutscenes, full-motion video cutscenes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCutscenes Context triple: [Lunar: Eternal Blue, hasCutscenes, full-motion video cutscenes]
-
A.
hasOpeningCreditsUsage
Indicates that something is used or appears specifically in the opening credits of a work.
-
B.
hasPostCreditsScene
Indicates that a film or episode includes a scene that appears during or after the closing credits.
-
C.
hasInteractiveFilm
Indicates that an entity is associated with, offers, or features an interactive film experience.
-
D.
hasShortFilmPrecursor
Indicates that a work is preceded by a short film that serves as an earlier or foundational version of it.
-
E.
hasDirectorCut
Indicates that a work (such as a film or episode) has an alternative version edited according to the director’s preferred vision.
- F. None of above. chosen
Provenance (4 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a7441c8190980c3516073422fe |
completed | March 31, 2026, 3:22 p.m. |
| PD | Predicate disambiguation | batch_69cbd111bf988190be98c92a607c6456 |
completed | March 31, 2026, 1:50 p.m. |
| PDg | Predicate description generation | batch_69cbe30d453481908f897ed2b06e7534 |
completed | March 31, 2026, 3:06 p.m. |
Created at: March 30, 2026, 6:18 p.m.