Triple
T20214255
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Akane |
E493574
|
entity |
| Predicate | protects |
P1040
|
FINISHED |
| Object | Sakura |
—
|
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: Sakura | Statement: [Akane, protects, Sakura]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sakura Context triple: [Akane, protects, Sakura]
-
A.
Sakura
Sakura is a Japanese high-speed Shinkansen train service that operates mainly on the Sanyo and Kyushu Shinkansen lines.
-
B.
Sakura
chosen
Sakura is a person whom Akane cares deeply about and actively tries to shield from harm or trouble.
-
C.
Sōsa
Sōsa is a coastal city in Chiba Prefecture, Japan, known for its proximity to the long sandy stretch of Kujūkuri Beach along the Pacific Ocean.
-
D.
Hana
Hana is a compassionate Canadian army nurse in Michael Ondaatje's novel "The English Patient," who cares for a badly burned man in an abandoned Italian villa during World War II.
-
E.
Hana
Hana is a common female given name of Hebrew origin, often associated with meanings like "grace" or "favor."
- 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_69da6269614c8190bb40475d9d477358 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e66ed8101081908e53a8bde48624b1 |
completed | April 20, 2026, 6:22 p.m. |
Created at: April 11, 2026, 11:38 p.m.