Triple
T24906651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mediterranean theater of operations |
E623726
|
entity |
| Predicate | primaryAdversaryType |
P68026
|
FINISHED |
| Object | corsairs |
—
|
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: corsairs | Statement: [Mediterranean theater of operations, primaryAdversaryType, corsairs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: primaryAdversaryType Context triple: [Mediterranean theater of operations, primaryAdversaryType, corsairs]
-
A.
primaryAntagonistType
Indicates the role or category of the main opposing force or adversary that serves as the central source of conflict.
-
B.
primaryAdversaryImplied
Indicates that an entity is understood or suggested, rather than explicitly stated, to be the main opponent or chief adversary of another entity.
-
C.
primaryAdversaryContext
chosen
Indicates the main opposing force or conflict-driving element that defines the central adversarial situation within a given context.
-
D.
primaryAdversaryDirection
Indicates the direction from an entity toward its main or most significant adversary.
-
E.
otherAdversary
Indicates that one entity is an adversary of another, distinct from any primary or previously identified adversary.
- 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_69e2fac797cc8190b30d77f4121099ac |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 18, 2026, 5:27 a.m.