Triple
T13109897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yume Kōjō: Doki Doki Panic |
E310941
|
entity |
| Predicate | enemyCharacter |
P108097
|
FINISHED |
| Object | Snifit |
E1023029
|
NE 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: Snifit | Statement: [Yume Kōjō: Doki Doki Panic, enemyCharacter, Snifit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Snifit Context triple: [Yume Kōjō: Doki Doki Panic, enemyCharacter, Snifit]
-
A.
Snifit
chosen
Snifit is a masked, cannon-mouthed enemy from the Mario series known for shooting projectiles instead of directly attacking like regular Shy Guys.
-
B.
Sniff
Sniff is a timid, treasure-loving creature and one of the main supporting characters in Tove Jansson’s Moomin series.
-
C.
Niffer
Niffer is the modern name for the archaeological site of ancient Nippur, a major religious and cultural center in Sumerian Mesopotamia.
-
D.
Scratch-N-Sniff
Scratch-N-Sniff is a scented, interactive feature—often used in books, stickers, or promotional materials—that releases a specific smell when its surface is rubbed.
-
E.
Sneezles
"Sneezles" is a humorous children's poem by A. A. Milne, featuring the character Christopher Robin suffering from an exaggerated case of the sneezes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d806a872d08190a329806f8ff30df4 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98bce3678819082a7aa1d83f20592 |
completed | April 10, 2026, 11:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6eadad81c8190881e6577e1c2a207 |
completed | May 3, 2026, 6:27 a.m. |
Created at: April 9, 2026, 9:05 p.m.