Triple
T35367719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kololo people |
E1021680
|
entity |
| Predicate | formedPolityWithName |
P196715
|
FINISHED |
| Object | Kololo kingdom |
—
|
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: Kololo kingdom | Statement: [Kololo people, formedPolityWithName, Kololo kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formedPolityWithName Context triple: [Kololo people, formedPolityWithName, Kololo kingdom]
-
A.
featuresPoliticalEntity
Indicates that something includes, presents, or prominently involves a political entity in its content or composition.
-
B.
hasPoliticalName
Indicates that an entity possesses a specific name or designation used in a political context or for political purposes.
-
C.
hasPolity
Indicates that one entity possesses, controls, or is associated with a particular political organization, governance structure, or state-like authority.
-
D.
politicalFormation
chosen
Indicates a relationship where an entity is established, organized, or constituted as a political body or governmental structure.
-
E.
analyzedPolity
Indicates that one entity has examined, studied, or evaluated the political structure, behavior, or characteristics of another entity (the polity).
- 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_69f76df000488190ab7c97f565677055 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a0056174c908190be99c91a70393e47 |
completed | May 10, 2026, 9:55 a.m. |
| PD | Predicate disambiguation | batch_6a00538e7e08819091ecd4316cd641a1 |
completed | May 10, 2026, 9:44 a.m. |
Created at: May 3, 2026, 4:03 p.m.