Triple
T34196566
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lozi King |
E877257
|
entity |
| Predicate | historicalPredecessorTitle |
P14662
|
FINISHED |
| Object | Litunga |
—
|
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 | Statement: [Lozi King, historicalPredecessorTitle, Litunga]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: historicalPredecessorTitle Context triple: [Lozi King, historicalPredecessorTitle, Litunga]
-
A.
predecessorTitleHolder
Indicates that one entity previously held a particular title or position before another entity.
-
B.
predecessorTitleContext
Indicates that the relationship specifies the contextual circumstances (such as role, period, or setting) under which a predecessor’s title is relevant or applies.
-
C.
historicalEntityPredecessor
chosen
Indicates that one historical entity existed or held a role before another, serving as its predecessor in time or sequence.
-
D.
predecessorEraRuler
Indicates that one ruler directly preceded another as the ruler of a given era or period.
-
E.
predecessorName
Indicates that the value is the name of an entity that directly precedes another in an ordered sequence or lineage.
- 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_6a004c41f13c8190bc47daf6a5ca3949 |
completed | May 10, 2026, 9:13 a.m. |
| PD | Predicate disambiguation | batch_6a004bce3e3081909b35ae5b3bf2b35e |
completed | May 10, 2026, 9:11 a.m. |
Created at: May 1, 2026, 1:55 a.m.