Triple
T33120681
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saudi Arabia–Yemen border area |
E847586
|
entity |
| Predicate | borderControlMeasures |
P121973
|
FINISHED |
| Object | border fence |
—
|
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 | Statement: [Saudi Arabia–Yemen border area, borderControlMeasures, border fence]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: borderControlMeasures Context triple: [Saudi Arabia–Yemen border area, borderControlMeasures, border fence]
-
A.
borderControlMeasure
chosen
Indicates a policy or action implemented to regulate, monitor, or restrict the movement of people or goods across a border.
-
B.
borderControlSide
Indicates that one entity is positioned on or associated with a particular side or segment of a border control area or checkpoint.
-
C.
borderControlRelevance
Indicates the extent to which something is pertinent or applicable to border control activities, policies, or decisions.
-
D.
borderControls
Indicates that one entity enforces or administers border control measures over another entity or at a specific boundary.
-
E.
borderControlDirection
Indicates the direction in which border control procedures are applied or enforced between two locations or jurisdictions.
- 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_69f3495751a081909850af5843da40dc |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69ff29d831b881908d485609e0fc1d0b |
completed | May 9, 2026, 12:34 p.m. |
| PD | Predicate disambiguation | batch_69ff28f9f9e4819087f3402735de66c7 |
completed | May 9, 2026, 12:30 p.m. |
Created at: May 1, 2026, 1:27 a.m.