Triple
T17454051
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Perilla frutescens |
E424985
|
entity |
| Predicate | parentTaxon |
P2891
|
FINISHED |
| Object | Perilla |
—
|
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: Perilla | Statement: [Perilla frutescens, parentTaxon, Perilla]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Perilla Context triple: [Perilla frutescens, parentTaxon, Perilla]
-
A.
Wasabi
Wasabi is a French action-comedy film known for its blend of fast-paced thrills and humor, directed by Gérard Krawczyk and starring Jean Reno.
-
B.
Wasabi
Wasabi is a cautious yet skilled member of the superhero team in Disney's animated film "Big Hero 6," known for his precision, laser-based weaponry, and rule-abiding personality.
-
C.
Shiso
Shiso is a small inland city in Japan’s Hyogo Prefecture known for its mountainous scenery, forests, and outdoor recreation.
-
D.
Perilla frutescens
chosen
Perilla frutescens is an aromatic annual herb widely used in East Asian cuisine and traditional medicine, known for its distinctive flavorful leaves and seeds.
-
E.
Ube
Ube is an industrial city in western Japan known for its chemical industry, cement production, and efforts to improve its environment and urban landscape.
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e451406c748190b5ac6aacff7a3cc7 |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.