Triple
T341316
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Berbers |
E6842
|
entity |
| Predicate | predates |
P97
|
FINISHED |
| Object | Arabization of North Africa |
—
|
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: Arabization of North Africa | Statement: [Berbers, predates, Arabization of North Africa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: predates Context triple: [Berbers, predates, Arabization of North Africa]
-
A.
predecessor
chosen
Indicates that one entity comes before another in an ordered sequence or succession.
-
B.
anticipates
Indicates that one entity expects or predicts a future event, action, or state involving another entity before it actually occurs.
-
C.
ancestor
Indicates that one entity is a forebear of another in a lineage, occurring in an earlier generation and connected through one or more parent-child relationships.
-
D.
precedentFor
Indicates that one situation, decision, or case serves as an authoritative example or basis for deciding or interpreting another.
-
E.
preysOn
Indicates that one entity hunts, kills, and consumes another entity as a food source.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eae611f88190955fbebe2b01835b |
completed | Feb. 28, 2026, 1:17 p.m. |
| PD | Predicate disambiguation | batch_69a2e95197fc8190820e8ebd0d7d27fa |
completed | Feb. 28, 2026, 1:10 p.m. |
Created at: Feb. 28, 2026, 1:08 p.m.