Triple
T18739220
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Legend of Zelda: Twilight Princess |
E458245
|
entity |
| Predicate | releaseDateJapanGameCube |
P31527
|
FINISHED |
| Object | 2006-12-02 |
—
|
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: 2006-12-02 | Statement: [The Legend of Zelda: Twilight Princess, releaseDateJapanGameCube, 2006-12-02]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: releaseDateJapanGameCube Context triple: [The Legend of Zelda: Twilight Princess, releaseDateJapanGameCube, 2006-12-02]
-
A.
releaseDateWiiUNorthAmerica
Indicates the calendar date on which something was released for the Wii U platform in North America.
-
B.
releaseDateJapan
chosen
Indicates the date on which something is officially released or made available in Japan.
-
C.
releaseDateSwitchWorldwide
Indicates the date on which a switch or transition is officially made available worldwide.
-
D.
releaseDateOnPlatform
Indicates the date on which a particular item (e.g., a product, game, or media) becomes available on a specific platform.
-
E.
releaseDateTaiwan
Indicates the date on which something (such as a product, film, or media) was officially released in Taiwan.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5768ca990819098102f8522ce401f |
completed | April 20, 2026, 12:42 a.m. |
| PD | Predicate disambiguation | batch_69e48d03766c8190a43f7681842f4f8d |
completed | April 19, 2026, 8:06 a.m. |
Created at: April 10, 2026, 11:51 a.m.