Triple
T30924291
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Independence of South Sudan |
E787814
|
entity |
| Predicate | flagLoweredOf |
P170305
|
FINISHED |
| Object | Sudan |
—
|
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: Sudan | Statement: [Independence of South Sudan, flagLoweredOf, Sudan]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: flagLoweredOf Context triple: [Independence of South Sudan, flagLoweredOf, Sudan]
-
A.
flagLoweringInvolves
Indicates that a flag-lowering event includes or entails participation, actions, or elements associated with a specified entity.
-
B.
lowered
Indicates that one entity caused another entity’s level, value, position, or intensity to become less than it was before.
-
C.
hasLower
Indicates that one entity is positioned at a lower level, rank, or value relative to another entity.
-
D.
loweredWhen
Indicates that one entity decreases or is reduced in value, level, or intensity when a specified condition involving another entity holds.
-
E.
flagUsedBy
Indicates that a particular flag is officially used by a specified entity, such as a country, organization, or group.
- F. None of above. chosen
Provenance (4 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_69f224bfaca88190b9d0dfcc86297fe9 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f692b82df881909350359a39daa9ff |
completed | May 3, 2026, 12:11 a.m. |
| PD | Predicate disambiguation | batch_69f68b7ec098819080480998038de940 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68c517f308190873c1c7e05a0c6d0 |
completed | May 2, 2026, 11:44 p.m. |
Created at: April 29, 2026, 8:51 p.m.