Triple
T9311052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gunthamund |
E224005
|
entity |
| Predicate | attemptedPolicy |
P58482
|
FINISHED |
| Object | maintaining Vandal naval power in the western Mediterranean |
—
|
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: maintaining Vandal naval power in the western Mediterranean | Statement: [Gunthamund, attemptedPolicy, maintaining Vandal naval power in the western Mediterranean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: attemptedPolicy Context triple: [Gunthamund, attemptedPolicy, maintaining Vandal naval power in the western Mediterranean]
-
A.
implementedPolicy
Indicates that a particular policy has been put into effect or carried out by an entity.
-
B.
attemptedAction
chosen
Indicates that an entity made an effort to perform a particular action, regardless of whether the action was successfully completed.
-
C.
targetedByPolicy
Indicates that an entity is the intended subject or focus of a specific policy’s rules, actions, or effects.
-
D.
laterPolicy
Indicates that one policy occurs or becomes effective after another policy in time.
-
E.
advancedPolicyOf
Indicates that one policy is a more developed, detailed, or progressive version of another policy.
- 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_69ca8425f4fc81909c1c586e9a5b7530 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd20ad3b20819092562c30e70a528f |
completed | April 1, 2026, 1:42 p.m. |
| PD | Predicate disambiguation | batch_69cc7a61e9a4819096eb014f3791ef2e |
completed | April 1, 2026, 1:52 a.m. |
Created at: March 30, 2026, 7:37 p.m.