Triple
T19006464
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sool region |
E465096
|
entity |
| Predicate | hasHumanitarianConcern |
P43054
|
FINISHED |
| Object | internal displacement |
—
|
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: internal displacement | Statement: [Sool region, hasHumanitarianConcern, internal displacement]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasHumanitarianConcern Context triple: [Sool region, hasHumanitarianConcern, internal displacement]
-
A.
hasHumanitarianAspect
chosen
Indicates that something involves, relates to, or has implications for humanitarian concerns such as human welfare, relief, or the protection of human rights.
-
B.
humanitarianCrisis
Indicates a situation in which a population faces severe, widespread threats to life, health, or basic living conditions that require urgent humanitarian assistance.
-
C.
hasHumanitarianPresence
Indicates that a humanitarian organization or effort is present and actively operating in relation to the referenced entity.
-
D.
humanRightsConcern
Indicates a situation, action, or condition that raises issues related to the recognition, protection, or violation of human rights.
-
E.
humanitarianAccess
Indicates that humanitarian actors are able to reach affected populations and deliver assistance safely, reliably, and without obstruction.
- 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_69d8dd01a56c81909694a128c66b21d7 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5d6a561848190bd957f248471c191 |
completed | April 20, 2026, 7:32 a.m. |
| PD | Predicate disambiguation | batch_69e4a2f88e0c81908cb20f08bf24cd32 |
completed | April 19, 2026, 9:40 a.m. |
Created at: April 10, 2026, 12:01 p.m.