Triple
T27675522
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2002 Maryland gubernatorial election |
E697767
|
entity |
| Predicate | percentageLoser |
P6370
|
FINISHED |
| Object | 47.7% |
—
|
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: 47.7% | Statement: [2002 Maryland gubernatorial election, percentageLoser, 47.7%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: percentageLoser Context triple: [2002 Maryland gubernatorial election, percentageLoser, 47.7%]
-
A.
loserPercentage
Indicates the proportion of entities in a group that have lost or failed according to a specified criterion.
-
B.
popularVotePercentageLoser
chosen
Indicates the percentage of the total popular vote received by the candidate or party that did not win the election.
-
C.
goalPercentage
Indicates the proportion of a goal that has been achieved relative to its total target.
-
D.
percentage
Indicates the proportion or share of one quantity relative to another, typically expressed as a value out of 100.
-
E.
marginOfVictoryPercentage
Indicates the percentage difference between the winner’s and the runner-up’s scores or votes in a contest or competition.
- 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_69ef590d458c81909583290c3cd0478b |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f65876c52c8190bc889c7a67bd07f3 |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575d89788190aca478e4aea05a65 |
completed | May 2, 2026, 7:58 p.m. |
Created at: April 27, 2026, 2:43 p.m.