Triple
T1307423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Melilla |
E27909
|
entity |
| Predicate | borderSecurityFeature |
P14206
|
FINISHED |
| Object | border fence with Morocco |
—
|
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: border fence with Morocco | Statement: [Melilla, borderSecurityFeature, border fence with Morocco]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderSecurityFeature Context triple: [Melilla, borderSecurityFeature, border fence with Morocco]
-
A.
borderRegime
Indicates the type, rules, or control system governing how movement or interaction is managed across a border between entities.
-
B.
borderConcern
Indicates a relationship where one entity has issues, disputes, or security considerations related to its shared boundary or border with another entity.
-
C.
borderEstablished
Indicates that a formal boundary between two geographic or political entities has been officially defined and put into effect.
-
D.
hasBorderFacilityType
chosen
Indicates that a border facility possesses or is classified by a specific type or category of border-related infrastructure or service.
-
E.
borderMonitored
Indicates that a border between two regions or entities is actively being watched, controlled, or surveilled.
- 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_69a496d7d83481908f83085854e51328 |
completed | March 1, 2026, 7:43 p.m. |
| NER | Named-entity recognition | batch_69a4c15490a88190872c3d2698a8f9c9 |
completed | March 1, 2026, 10:44 p.m. |
| PD | Predicate disambiguation | batch_69a4bee9e4a88190b22ab2ee831a23c9 |
completed | March 1, 2026, 10:34 p.m. |
Created at: March 1, 2026, 7:51 p.m.