Triple
T14023196
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 空母「赤城」 |
E337386
|
entity |
| Predicate | 改装 |
P3155
|
FINISHED |
| Object | 多段飛行甲板から一段飛行甲板への改装 |
—
|
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: 多段飛行甲板から一段飛行甲板への改装 | Statement: [空母「赤城」, 改装, 多段飛行甲板から一段飛行甲板への改装]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 改装 Context triple: [空母「赤城」, 改装, 多段飛行甲板から一段飛行甲板への改装]
-
A.
modification
Indicates a change made to an existing entity, altering its properties, structure, or state from a prior version.
-
B.
refit
chosen
Indicates that an existing object or structure is being modified, repaired, or equipped with new parts or features to restore or improve its function.
-
C.
aircraftModification
Indicates a relationship where an aircraft undergoes a change, upgrade, or alteration to its structure, systems, or configuration.
-
D.
modificationProgram
Indicates that an entity is subject to, or associated with, a program or process that alters, updates, or changes its properties or state.
-
E.
decorChanges
Indicates that an entity alters or updates the decorative appearance or arrangement of another entity or environment.
- 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.