Triple
T21090451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese Secret Service (in film) |
E519622
|
entity |
| Predicate | notableMember |
P10
|
FINISHED |
| Object | Aki |
—
|
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: Aki | Statement: [Japanese Secret Service (in film), notableMember, Aki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aki Context triple: [Japanese Secret Service (in film), notableMember, Aki]
-
A.
Aki
chosen
Aki is a Japanese given name and name component that can be used for various masculine or unisex names, often carrying meanings related to brightness, autumn, or clarity depending on the kanji used.
-
B.
Akie
Akie is the given name of Akie Abe, the Japanese radio DJ and socialite who served as the wife of former Prime Minister Shinzō Abe.
-
C.
Akaki
Akaki is a Georgian masculine given name most notably borne by the prominent 19th-century poet and national figure Akaki Tsereteli.
-
D.
Aoki
Aoki is a Japanese surname borne by various notable figures in entertainment, sports, and business.
-
E.
Akiek
Akiek are an Indigenous hunter-gatherer community of East Africa, closely related to the Okiek people and traditionally associated with forest-based livelihoods in Kenya and Tanzania.
- 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_69e0b507dd9081908fb8bfcbef4c8b46 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7094ea7f881909db83bf6961b41ec |
completed | April 21, 2026, 5:21 a.m. |
Created at: April 16, 2026, 2:50 p.m.