Triple
T20091987
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Katsuya Okada |
E496293
|
entity |
| Predicate | familyName |
P18
|
FINISHED |
| Object | Okada |
—
|
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: Okada | Statement: [Katsuya Okada, familyName, Okada]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Okada Context triple: [Katsuya Okada, familyName, Okada]
-
A.
Okada
chosen
Okada is a common Japanese surname borne by numerous notable figures in fields such as sports, politics, and entertainment.
-
B.
Okada Manila
Okada Manila is a large luxury integrated resort and casino complex in Metro Manila, Philippines, known for its opulent accommodations, gaming facilities, and entertainment attractions.
-
C.
Owada
Owada is a Japanese surname most notably borne by Empress Masako of Japan and her family.
-
D.
Tokashiki
Tokashiki is a small island municipality in Okinawa Prefecture, Japan, known for its clear waters, coral reefs, and popular diving and snorkeling spots within the Kerama Islands.
-
E.
Okisada
Okisada was the personal name of Emperor Sanjō, a Heian-period Japanese emperor of the early 11th century.
- 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_69da626eee3881909f3454986d4a6511 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6655edde08190a3f950e7f0c7cf9c |
completed | April 20, 2026, 5:41 p.m. |
Created at: April 11, 2026, 11:22 p.m.