Triple
T28062953
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ciskei |
E709163
|
entity |
| Predicate | hadOwnDefenseForce |
P104865
|
FINISHED |
| Object | Ciskei Defence Force |
—
|
NE NERFINISHED |
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: Ciskei Defence Force | Statement: [Ciskei, hadOwnDefenseForce, Ciskei Defence Force]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadOwnDefenseForce Context triple: [Ciskei, hadOwnDefenseForce, Ciskei Defence Force]
-
A.
hasArmedForces
chosen
Indicates that an entity possesses or maintains organized military forces under its control.
-
B.
hasReserveForces
Indicates that an entity possesses additional military or security personnel kept in reserve for potential future deployment or use.
-
C.
hasOwnPoliceForce
Indicates that an entity maintains and controls its own dedicated police force or law enforcement agency.
-
D.
defenseForces
Indicates a relationship where one entity serves as the military or protective force responsible for defending another entity.
-
E.
defensiveCapability
Indicates the ability or capacity of an entity to protect itself or others against threats, attacks, or harm.
- 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_69ef9b6eb6d88190a3fea236eb0f7bed |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f643ed0b7481908cf25f3afec0a61d |
completed | May 2, 2026, 6:35 p.m. |
| PD | Predicate disambiguation | batch_69f641def1e88190a05bf865ced78b23 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 27, 2026, 8:41 p.m.