Triple
T32712870
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KANU |
E836444
|
entity |
| Predicate | defeatedByCoalition |
P11263
|
FINISHED |
| Object | National Rainbow Coalition |
—
|
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: National Rainbow Coalition | Statement: [KANU, defeatedByCoalition, National Rainbow Coalition]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defeatedByCoalition Context triple: [KANU, defeatedByCoalition, National Rainbow Coalition]
-
A.
resultedInCoalitionIncluding
Indicates that one event, action, or circumstance led to the formation of a coalition that included a specified participant or set of participants.
-
B.
formedByCoalition
Indicates that something (such as a group, government, or organization) came into existence through the alliance or joint effort of multiple distinct parties or factions.
-
C.
hasCoalition
Indicates that an entity participates in, belongs to, or is associated with a coalition formed with one or more other entities.
-
D.
defeatedBy
chosen
Indicates that one entity has been beaten, overcome, or conquered by another in a contest, conflict, or competition.
-
E.
loserCoalition
Indicates a coalition of entities that collectively fail to win or achieve a desired outcome in a competitive or decision-making context.
- 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_69f3493446148190819541f3ffe79975 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6cd126fcc8190aa1f1f146e45ec0c |
completed | May 3, 2026, 4:20 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1470808190b70cdfd7a6395670 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:11 a.m.