Triple
T24731043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Korandjé |
E618287
|
entity |
| Predicate | contactZone |
P2160
|
FINISHED |
| Object | Berber–Arabic–Songhay contact area |
—
|
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: Berber–Arabic–Songhay contact area | Statement: [Korandjé, contactZone, Berber–Arabic–Songhay contact area]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: contactZone Context triple: [Korandjé, contactZone, Berber–Arabic–Songhay contact area]
-
A.
contactWith
Indicates that two entities are in direct or indirect physical or communicative interaction or touch with each other.
-
B.
collisionZone
Indicates a spatial region within which objects are considered to be in contact or impact with one another, typically used to detect or handle collisions.
-
C.
contactPhenomena
Indicates a relationship where two or more physical phenomena come into direct interaction or touch with each other.
-
D.
technicalContact
Indicates that one entity serves as the primary point of contact for technical issues, support, or maintenance related to another entity.
-
E.
zone
chosen
Indicates that an entity is located within, associated with, or assigned to a particular geographic or conceptual area or zone.
- 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_69e2fab772608190b74163751047ff50 |
completed | April 18, 2026, 3:29 a.m. |
| NER | Named-entity recognition | batch_69f6352fdb788190b9bad30243690743 |
completed | May 2, 2026, 5:32 p.m. |
| PD | Predicate disambiguation | batch_69f63182f1408190bddc1214fcbd6145 |
completed | May 2, 2026, 5:16 p.m. |
Created at: April 18, 2026, 4:02 a.m.