Triple
T30202559
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ULIMO-K |
E767819
|
entity |
| Predicate | disarmedInContextOf |
P158510
|
FINISHED |
| Object | Liberian peace process |
—
|
NE NERFINISHED |
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: Liberian peace process | Statement: [ULIMO-K, disarmedInContextOf, Liberian peace process]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: disarmedInContextOf Context triple: [ULIMO-K, disarmedInContextOf, Liberian peace process]
-
A.
unarmed
Indicates that an entity is not carrying or equipped with any weapons.
-
B.
exceptionToDisarmament
Indicates that a specific case or situation is exempt from otherwise applicable disarmament rules or obligations.
-
C.
requiredDisarmamentOf
Indicates that one entity is obligated to remove, disable, or reduce the weapons or military capabilities of another entity.
-
D.
brokenInContextOf
Indicates that something is damaged, malfunctioning, or not functioning as intended specifically within a given situation, environment, or usage context.
-
E.
demilitarizationContext
chosen
Indicates the process or circumstances in which military forces, capabilities, or infrastructure are reduced, removed, or prohibited within a specific area or situation.
- 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_69f2247eb0848190b4032f302d39c0d9 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67fc600d48190a9d19b86a53677f3 |
completed | May 2, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69f6760216108190bbb708d53a6c2c25 |
completed | May 2, 2026, 10:09 p.m. |
Created at: April 29, 2026, 7:31 p.m.