Triple
T31250648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yokosuka aircraft |
E796806
|
entity |
| Predicate | successorUser |
P198439
|
FINISHED |
| Object | Japan Maritime Self-Defense Force (indirect, institutional) |
—
|
NE NERFINISHED |
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: Japan Maritime Self-Defense Force (indirect, institutional) | Statement: [Yokosuka aircraft, successorUser, Japan Maritime Self-Defense Force (indirect, institutional)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorUser Context triple: [Yokosuka aircraft, successorUser, Japan Maritime Self-Defense Force (indirect, institutional)]
-
A.
successorUse
Indicates that one entity is used or applied as the subsequent or follow-up use of another entity in a sequence or lifecycle.
-
B.
successorStateUser
Indicates that one user state directly follows another as its immediate successor in a sequence of states.
-
C.
successor
Indicates that one entity directly follows another in an ordered sequence or position.
-
D.
successorRole
Indicates that one role or position directly follows and replaces another in a sequence or organizational structure.
-
E.
predecessorUser
Indicates that one user previously held a role, position, or state that is now held by another user, making the first user the predecessor of the second.
- F. None of above. chosen
Provenance (4 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_69f224dc84d0819081f1cb6f9127e6b1 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fee335cb08819097e3a0e09d5ebf49 |
completed | May 9, 2026, 7:33 a.m. |
| PD | Predicate disambiguation | batch_69fee2c74fd88190acfc045ab07b7f6b |
completed | May 9, 2026, 7:31 a.m. |
| PDg | Predicate description generation | batch_69fee33485188190a43526c9d39e3b6a |
completed | May 9, 2026, 7:33 a.m. |
Created at: April 29, 2026, 9:11 p.m.