Triple
T20687442
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gemini |
E508455
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Firebreather |
—
|
NE NERFINISHED |
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: Firebreather | Statement: [Gemini, hasPart, Firebreather]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Firebreather Context triple: [Gemini, hasPart, Firebreather]
-
A.
Firebreather
chosen
Firebreather is an animated superhero film based on the Image Comics series, following a teenage half-human, half-dragon as he struggles to balance high school life with his monstrous heritage.
-
B.
Dragon's Breath
"Dragon's Breath" is a children's fantasy novel by E. D. Baker, continuing the adventures of a young princess who can turn into a dragon in a humorous, magical world.
-
C.
Fireblast
Fireblast is the Mage class’s basic hero power in Hearthstone, dealing a small amount of direct damage to any chosen target.
-
D.
Scorch the Dragon
Scorch the Dragon is the fiery dragon mascot representing Minnesota State University Moorhead’s athletic teams and school spirit.
-
E.
Fireburn
Fireburn was a hardcore punk band known for its politically charged lyrics and featuring notable musicians from the punk and metal scenes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beaddfe88190897b8963fa8b2245 |
completed | April 21, 2026, 12:02 a.m. |
Created at: April 16, 2026, 11:45 a.m.