Triple
T34196526
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barotse Province |
E877256
|
entity |
| Predicate | hadTraditionalAuthority |
P108031
|
FINISHED |
| Object | Litunga of Barotseland |
—
|
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: Litunga of Barotseland | Statement: [Barotse Province, hadTraditionalAuthority, Litunga of Barotseland]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadTraditionalAuthority Context triple: [Barotse Province, hadTraditionalAuthority, Litunga of Barotseland]
-
A.
traditionalAuthorityOver
Indicates that one entity holds customary or historically established power, control, or decision-making authority over another entity.
-
B.
hasTraditionalInstitutions
Indicates that an entity possesses or is associated with long-established, customary social, cultural, or governance institutions.
-
C.
hasTraditionalRulers
chosen
Indicates that one entity possesses or is governed by traditional rulers associated with it.
-
D.
hadSecularAuthority
Indicates that an entity possessed or exercised non-religious, civil, or governmental authority over others or over a territory.
-
E.
traditionalMonarchy
Indicates a system where a monarchy operates according to long-established customs, hereditary succession, and historical institutions rather than modern or codified reforms.
- 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_69f349af20a4819089ac24d28f2d8112 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f710296d748190badcd84374991840 |
completed | May 3, 2026, 9:06 a.m. |
| PD | Predicate disambiguation | batch_69f70f3c5bfc81908585f52e196dafe5 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:55 a.m.