Triple
T5936651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 吉田茂 |
E132059
|
entity |
| Predicate | 関連人物 |
P37304
|
FINISHED |
| Object | マッカーサー |
E1852
|
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: マッカーサー | Statement: [吉田茂, 関連人物, マッカーサー]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: マッカーサー Context triple: [吉田茂, 関連人物, マッカーサー]
-
A.
Douglas MacArthur
chosen
Douglas MacArthur was a prominent American five-star general who played a leading role in the Pacific theater during World War II and later oversaw the Allied occupation of Japan.
-
B.
Malcolm MacArthur
Malcolm MacArthur was a son of American Civil War general and later U.S. President James A. Garfield’s wife, Mary Pinkney Hardy (Mollie) MacArthur.
-
C.
Malcolm MacArthur
Malcolm MacArthur was the son of Mary Pinkney Hardy MacArthur and part of the prominent MacArthur family connected to U.S. General Douglas MacArthur.
-
D.
MacArthur
MacArthur is a Scottish-origin surname notably borne by several prominent American military figures and public personalities.
-
E.
MacArthur
MacArthur is a small unincorporated community located in Raleigh County, West Virginia, United States.
- 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_69c0085c55dc8190aa90e242c956e2fa |
completed | March 22, 2026, 3:18 p.m. |
| NER | Named-entity recognition | batch_69c038eca9688190adeed21df058daf1 |
completed | March 22, 2026, 6:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0c06f979881908d7e98ee674f1ff2 |
completed | March 23, 2026, 4:24 a.m. |
Created at: March 22, 2026, 4:01 p.m.