Triple
T16523790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viriathus |
E401383
|
entity |
| Predicate | militaryOpponents |
P117522
|
FINISHED |
| Object | Roman provincial authorities in Hispania |
—
|
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: Roman provincial authorities in Hispania | Statement: [Viriathus, militaryOpponents, Roman provincial authorities in Hispania]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: militaryOpponents Context triple: [Viriathus, militaryOpponents, Roman provincial authorities in Hispania]
-
A.
warAdversary
chosen
Indicates that two entities are opponents or enemies engaged in a state of war or armed conflict.
-
B.
opposingMilitaryBranch
Indicates that two military branches belong to opposing or enemy forces in a conflict or strategic context.
-
C.
opposedWar
Indicates that an entity actively resisted, disagreed with, or worked against a particular war or military conflict.
-
D.
commandedForcesAgainst
Indicates that one entity held command authority over military or armed forces engaged in opposition to another entity.
-
E.
historicalEnemies
Indicates that the entities have been enemies of each other over a significant period in history.
- 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_69d883838abc8190bc79cb2d41733ce2 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e32ed2622c8190b6429a49ca92284a |
completed | April 18, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69e296995d388190b88ebe189dce890d |
completed | April 17, 2026, 8:22 p.m. |
Created at: April 10, 2026, 5:14 a.m.