Triple
T28062952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ciskei |
E709163
|
entity |
| Predicate | hadOwnPoliceForce |
P86939
|
FINISHED |
| Object |
Ciskei Police
The Ciskei Police was the law enforcement agency of the former apartheid-era Bantustan of Ciskei in South Africa.
|
E1805143
|
NE FINISHED |
How this triple was built (3 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 Police | Statement: [Ciskei, hadOwnPoliceForce, Ciskei Police]
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ciskei Police Triple: [Ciskei, hadOwnPoliceForce, Ciskei Police]
Generated description
The Ciskei Police was the law enforcement agency of the former apartheid-era Bantustan of Ciskei in South Africa.
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadOwnPoliceForce Context triple: [Ciskei, hadOwnPoliceForce, Ciskei Police]
-
A.
hasOwnPoliceForce
chosen
Indicates that an entity maintains and controls its own dedicated police force or law enforcement agency.
-
B.
hasPoliceInstitution
Indicates that an entity is associated with, governed by, or served by a particular police institution or law enforcement body.
-
C.
hasPoliceDepartment
Indicates that an entity possesses, is served by, or is administratively associated with a police department.
-
D.
hadImportantPoleis
Indicates that a region, state, or culture possessed one or more significant city-states (poleis) that played major political, economic, or cultural roles.
-
E.
hadAutonomousEstates
Indicates that the related entity possessed or controlled self-governing estates or territories that operated with a significant degree of autonomy.
- F. None of above.
Provenance (6 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_69f64018804c81909397f6bcf1ab0dea |
completed | May 2, 2026, 6:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a15d78ec1d8819088cbfa1ee9897a60 |
completed | May 26, 2026, 5:25 p.m. |
| NEDg | Description generation | batch_6a15db1a4ac0819094b2b299c3df5516 |
completed | May 26, 2026, 5:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a15dbc8593c81908624b135c3a72029 |
completed | May 26, 2026, 5:43 p.m. |
| PD | Predicate disambiguation | batch_69f63c6a8474819091b8c6fe98e3862d |
completed | May 2, 2026, 6:03 p.m. |
Created at: April 27, 2026, 8:41 p.m.