Triple
T23122179
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Kambula |
E576923
|
entity |
| Predicate | BritishTactics |
P50132
|
FINISHED |
| Object | defensive laager |
—
|
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: defensive laager | Statement: [Battle of Kambula, BritishTactics, defensive laager]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: BritishTactics Context triple: [Battle of Kambula, BritishTactics, defensive laager]
-
A.
EnglishTactic
Indicates a tactical or strategic action carried out using the English language as the primary medium or method.
-
B.
strengthBritishForces
Indicates the numerical size or combat capacity of British military forces in a given context or operation.
-
C.
strength_British_side
Indicates the level or measure of military or strategic power possessed by the British side in a given context.
-
D.
militaryForceInvolved (British)
Indicates that the British military forces participated in or were involved in the referenced event or action.
-
E.
tacticalStyle
chosen
Indicates the characteristic way in which an entity plans and executes actions or maneuvers to achieve its objectives.
- 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e50c500819095d59aef44388153 |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.