Triple
T15919240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kokuritsu Kyōgijō |
E386048
|
entity |
| Predicate | structuralEngineer |
P616
|
FINISHED |
| Object | Azusa Sekkei |
E386046
|
NE FINISHED |
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: Azusa Sekkei | Statement: [Kokuritsu Kyōgijō, structuralEngineer, Azusa Sekkei]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Azusa Sekkei Context triple: [Kokuritsu Kyōgijō, structuralEngineer, Azusa Sekkei]
-
A.
Azusa Sekkei
chosen
Azusa Sekkei is a prominent Japanese architectural and engineering firm known for designing major sports and public facilities.
-
B.
Daisaku
Daisaku is a Japanese given name most notably borne by Daisaku Ikeda, the Buddhist philosopher, educator, and longtime president of the Soka Gakkai movement.
-
C.
Kotoku Sato
Kotoku Sato was a Japanese lieutenant general in World War II who led the 31st Division during the Burma Campaign, including the ill-fated offensive toward Kohima in India.
-
D.
Isamu
Isamu is a Japanese given name commonly used for males, often associated with meanings related to courage or bravery.
-
E.
Rokkō Airando
Rokkō Airando is a man-made island in Kobe, Japan, known for its residential areas, commercial facilities, and port-related infrastructure.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e15680c7b881909150f8b53bc058d4 |
completed | April 16, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffb5a79b808190850fa9d327f7ef72 |
completed | May 9, 2026, 10:31 p.m. |
Created at: April 10, 2026, 4:52 a.m.