Triple
T9439119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kanem Empire |
E227595
|
entity |
| Predicate | sourceOfHistory |
P1823
|
FINISHED |
| Object | Arabic chronicles |
—
|
LITERAL FINISHED |
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: Arabic chronicles | Statement: [Kanem Empire, sourceOfHistory, Arabic chronicles]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sourceOfHistory Context triple: [Kanem Empire, sourceOfHistory, Arabic chronicles]
-
A.
historicalOrigin
chosen
Indicates the relationship by which one entity serves as the source, origin, or starting point in history for another entity.
-
B.
historicalEvidence
Indicates that there exists documented or otherwise verifiable information supporting the occurrence, authenticity, or truth of a past event, state, or relationship between entities.
-
C.
historicalReference
Indicates that one entity refers to, cites, or alludes to another entity from an earlier time or historical context.
-
D.
historicalSee
Indicates that one entity observed, encountered, or took visual notice of another entity in the past.
-
E.
historicalBackground
Indicates that one entity provides contextual historical information or circumstances that help explain the origin, development, or significance of another entity.
- 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_69ca843884488190ad6cbe0153088234 |
completed | March 30, 2026, 2:10 p.m. |
| NER | Named-entity recognition | batch_69cd7ee1c8c48190a2ae8673eee07e9a |
completed | April 1, 2026, 8:24 p.m. |
| PD | Predicate disambiguation | batch_69cca55548488190b171ae695a3212de |
completed | April 1, 2026, 4:55 a.m. |
Created at: March 30, 2026, 7:50 p.m.