Triple
T12410398
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2011 Nigerian presidential election |
E296498
|
entity |
| Predicate | percentageForGoodluckJonathan |
P92182
|
FINISHED |
| Object | about 59% |
—
|
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: about 59% | Statement: [2011 Nigerian presidential election, percentageForGoodluckJonathan, about 59%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageForGoodluckJonathan Context triple: [2011 Nigerian presidential election, percentageForGoodluckJonathan, about 59%]
-
A.
goalPercentage
Indicates the proportion of a goal that has been achieved relative to its total target.
-
B.
supportedByFortuneFrom
Indicates that an entity’s success, status, or outcome is attributed to favorable luck or fortune originating from a particular source.
-
C.
percentage
chosen
Indicates the proportion or share of one quantity relative to another, typically expressed as a value out of 100.
-
D.
percentageForJohnTory
Indicates the percentage value associated with John Tory in a given context, such as votes, support, or another measurable metric.
-
E.
hallOfFameVotePercentage
Indicates the percentage of votes an individual received in a Hall of Fame selection process.
- 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_69d6ad9f464c81909db36d7e96e34b9e |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94e1888b48190bd750f839a26e99e |
completed | April 10, 2026, 7:23 p.m. |
| PD | Predicate disambiguation | batch_69d94d354b488190adc83fb4f2770dd5 |
completed | April 10, 2026, 7:19 p.m. |
Created at: April 8, 2026, 9:55 p.m.