Triple
T3259693
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Songhai Empire |
E68378
|
entity |
| Predicate | armyType |
P6154
|
FINISHED |
| Object | cavalry-based army |
—
|
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: cavalry-based army | Statement: [Songhai Empire, armyType, cavalry-based army]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: armyType Context triple: [Songhai Empire, armyType, cavalry-based army]
-
A.
typeOfTroops
chosen
Indicates the specific category or kind of military forces involved in or associated with an entity or event.
-
B.
militaryOrganization
Indicates that an entity functions as, or is associated with, a structured armed forces or defense-related organization.
-
C.
isRegularArmyUnit
Indicates that the entity functions as a formal, organized military unit within a country's regular (non-irregular) armed forces.
-
D.
groundForces
Indicates that one entity deploys, commands, or involves military forces operating on land in relation to another entity or context.
-
E.
countryMilitary
Indicates that a country possesses, controls, or is associated with a particular military force or armed organization.
- 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_69ad858f74408190bcbd07f967cd7bd0 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adafa673a481909b5024b4e0e1c2a7 |
completed | March 8, 2026, 5:19 p.m. |
| PD | Predicate disambiguation | batch_69ada41ae74081909a0d1d696be8e35e |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:09 p.m.