Triple
T31082636
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Fada |
E792141
|
entity |
| Predicate | opponentEquipment |
P60742
|
FINISHED |
| Object | Libyan armored units |
—
|
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: Libyan armored units | Statement: [Battle of Fada, opponentEquipment, Libyan armored units]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: opponentEquipment Context triple: [Battle of Fada, opponentEquipment, Libyan armored units]
-
A.
opponentAsset
Indicates that one entity is an asset, resource, or property belonging to or controlled by an opponent of another entity.
-
B.
opponentDescriptor
Indicates how an opposing party in a conflict, competition, or interaction is characterized or described in relation to another entity.
-
C.
associatedOpponent
Indicates that one entity is recognized or designated as an opponent or adversary associated with another entity in a given context.
-
D.
featuresOpponentType
Indicates that an entity involves, includes, or is associated with an opponent of a specified type within a competitive or adversarial context.
-
E.
opponentForceCharacteristic
chosen
Indicates a characteristic or attribute that describes the nature, capability, or condition of an opposing force.
- 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_69f224ce48348190bd0fc23f656ed683 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f6afebd7ec8190ab696f363d84abf0 |
completed | May 3, 2026, 2:16 a.m. |
| PD | Predicate disambiguation | batch_69f6aca3dedc81908b519d53d2909868 |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 29, 2026, 9:02 p.m.