Triple
T23257819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ahmad Tejan Kabbah |
E581918
|
entity |
| Predicate | wasReelectedIn |
P28286
|
FINISHED |
| Object | 2002 Sierra Leonean presidential election |
—
|
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: 2002 Sierra Leonean presidential election | Statement: [Ahmad Tejan Kabbah, wasReelectedIn, 2002 Sierra Leonean presidential election]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasReelectedIn Context triple: [Ahmad Tejan Kabbah, wasReelectedIn, 2002 Sierra Leonean presidential election]
-
A.
reElectedToPresidency
Indicates that an individual, having previously served as president, is chosen again to hold the office of the presidency.
-
B.
reElectionOf
chosen
Indicates that an entity is being elected again to a position or office they have previously held.
-
C.
incumbentRanForReelection
Indicates that a current officeholder sought to be elected again to the same position in a subsequent election.
-
D.
reElectionYear
Indicates the year in which an entity is (or is scheduled to be) elected again to the same position or office.
-
E.
eligibleForReelectionAfter
Indicates that an individual is permitted, under the relevant rules or laws, to run again for a position or office after a specified time or condition is met.
- 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_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194c5f5bc8190ac8776f7f7430209 |
completed | April 29, 2026, 5:19 a.m. |
| PD | Predicate disambiguation | batch_69effce4d704819092826931d430e8c4 |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:11 p.m.