Triple
T1604834
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Blood River |
E34477
|
entity |
| Predicate | strengthZulu |
P6664
|
FINISHED |
| Object | estimated 10,000–20,000 warriors |
—
|
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: estimated 10,000–20,000 warriors | Statement: [Battle of Blood River, strengthZulu, estimated 10,000–20,000 warriors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: strengthZulu Context triple: [Battle of Blood River, strengthZulu, estimated 10,000–20,000 warriors]
-
A.
strengthPeak
Indicates the point or period at which an entity’s strength reaches its maximum level.
-
B.
strength
chosen
Indicates the degree of power, intensity, or effectiveness with which an entity can act on, influence, or withstand another entity or force.
-
C.
strengthDescription
Indicates a description or characterization of the degree of strength associated with an entity or relationship.
-
D.
isStrongerThan
Indicates that one entity possesses greater physical power, force, or effectiveness than another entity.
-
E.
strongerThan
Indicates that one entity possesses greater strength, power, or intensity than another.
- 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_69a885fea6a481909fe83ba6441f1774 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a93fa6926081908bc78d15c0be3185 |
completed | March 5, 2026, 8:32 a.m. |
| PD | Predicate disambiguation | batch_69a907c35f848190a2428c52e81d013e |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:28 p.m.