Triple
T19570143
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Operation A-Go |
E489686
|
entity |
| Predicate | involvedAsset |
P113316
|
FINISHED |
| Object | Japanese aircraft carriers |
—
|
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: Japanese aircraft carriers | Statement: [Operation A-Go, involvedAsset, Japanese aircraft carriers]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: involvedAsset Context triple: [Operation A-Go, involvedAsset, Japanese aircraft carriers]
-
A.
asset
chosen
Indicates that one entity is a valuable resource, item, or property owned, controlled, or beneficially used by another entity.
-
B.
tradedAsset
Indicates that an entity is the asset or instrument being exchanged in a trade transaction between parties.
-
C.
assetType
Indicates the specific category or classification of an asset within a broader asset framework or system.
-
D.
materialInvolved
Indicates that a particular material participates in, is used by, or is otherwise involved in the referenced process, event, or relationship.
-
E.
involvedAction
Indicates that an entity participates in, performs, or is otherwise engaged in a specified action or activity.
- 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_69d8e8dd9374819098e36349b3211663 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6402043588190a99f5a55c5dcd8a6 |
completed | April 20, 2026, 3:02 p.m. |
| PD | Predicate disambiguation | batch_69e514d4df3c8190b7e9b3b4fdf9452a |
completed | April 19, 2026, 5:45 p.m. |
Created at: April 10, 2026, 1:42 p.m.