Triple
T31091057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS-18 Mod 5 |
E792385
|
entity |
| Predicate | successorStateUser |
P198238
|
FINISHED |
| Object | Russian Strategic Rocket Forces |
—
|
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: Russian Strategic Rocket Forces | Statement: [SS-18 Mod 5, successorStateUser, Russian Strategic Rocket Forces]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: successorStateUser Context triple: [SS-18 Mod 5, successorStateUser, Russian Strategic Rocket Forces]
-
A.
successorState
Indicates that one state directly follows another as the immediate next state in a sequence or process.
-
B.
successorStateUse
Indicates that one state or condition directly follows and is used as the next state resulting from a prior state or action.
-
C.
successorStateOwner
Indicates that one entity becomes the new or subsequent owner of something previously owned by another entity.
-
D.
hasSuccessorUsers
Indicates that one user or set of users is followed or replaced by another user or set of users in a sequence or succession.
-
E.
laterUser
Indicates that one user occurs or is positioned temporally after another user in a sequence or timeline.
- 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_69f224ce48348190bd0fc23f656ed683 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69fed48d8e148190a99c0aea29f8a3ee |
completed | May 9, 2026, 6:30 a.m. |
| PD | Predicate disambiguation | batch_69fed3c82a24819095e614e31ac0307f |
completed | May 9, 2026, 6:27 a.m. |
| PDg | Predicate description generation | batch_69fed48c92ec8190b3be88880d86de86 |
completed | May 9, 2026, 6:30 a.m. |
Created at: April 29, 2026, 9:02 p.m.