Triple
T6603036
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Japanese destroyer Ayanami |
E149046
|
entity |
| Predicate | sawAction |
P59465
|
FINISHED |
| Object | early Pacific campaigns of World War II |
—
|
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: early Pacific campaigns of World War II | Statement: [Japanese destroyer Ayanami, sawAction, early Pacific campaigns of World War II]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sawAction Context triple: [Japanese destroyer Ayanami, sawAction, early Pacific campaigns of World War II]
-
A.
sawActionDuring
Indicates that one entity observed an action or event occurring within a specific time period or during another event.
-
B.
sawActionOn
Indicates that one entity visually perceived another entity performing an action.
-
C.
firstSawAction
Indicates that one entity was the earliest or initial observer of a particular action performed by another entity.
-
D.
involvedAction
chosen
Indicates that an entity participates in, performs, or is otherwise engaged in a specified action or activity.
-
E.
allegedAction
Indicates that an action is claimed or asserted to have occurred, typically without being proven or confirmed.
- 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_69c687eaa7508190bb58ce2aa02039b3 |
completed | March 27, 2026, 1:36 p.m. |
| NER | Named-entity recognition | batch_69c6cc9c6cb0819084fec8e0beb430de |
completed | March 27, 2026, 6:29 p.m. |
| PD | Predicate disambiguation | batch_69c6acfd17388190bd0bb8b2371e7df1 |
completed | March 27, 2026, 4:14 p.m. |
Created at: March 27, 2026, 1:56 p.m.