Triple
T14023201
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 空母「赤城」 |
E337386
|
entity |
| Predicate | 条約による改造 |
P73191
|
FINISHED |
| Object | ワシントン海軍軍縮条約に基づき空母へ改造 |
—
|
LITERAL 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: ワシントン海軍軍縮条約に基づき空母へ改造 | Statement: [空母「赤城」, 条約による改造, ワシントン海軍軍縮条約に基づき空母へ改造]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 条約による改造 Context triple: [空母「赤城」, 条約による改造, ワシントン海軍軍縮条約に基づき空母へ改造]
-
A.
reformedByTreaty
chosen
Indicates that an existing entity has been reorganized or restructured as a result of the terms of a formal treaty.
-
B.
treaty
Indicates a formal, negotiated agreement or pact established between entities, typically states or organizations, that defines mutual obligations, rights, or terms of cooperation.
-
C.
cededByTreaty
Indicates that control or ownership of one entity was formally transferred to another entity as a result of a treaty or formal agreement.
-
D.
treatyOf
Indicates a formal agreement or pact established between entities, typically states or organizations, defining their mutual obligations or terms.
-
E.
treatyRevisionOutcome
Indicates the result or consequence of a process to revise or amend a treaty.
- F. None of above.
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_69d81c6543a48190bd5ba93d7419e797 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de2f3d87b88190b038d334f4965369 |
completed | April 14, 2026, 12:12 p.m. |
| PD | Predicate disambiguation | batch_69de05a802ac819090604025aae6a4d5 |
completed | April 14, 2026, 9:15 a.m. |
Created at: April 9, 2026, 10:19 p.m.