Triple
T15718945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2021 London mayoral election |
E381035
|
entity |
| Predicate | firstRoundVoteShareOfMainOpponent |
P68283
|
FINISHED |
| Object | 35.3% |
—
|
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: 35.3% | Statement: [2021 London mayoral election, firstRoundVoteShareOfMainOpponent, 35.3%]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstRoundVoteShareOfMainOpponent Context triple: [2021 London mayoral election, firstRoundVoteShareOfMainOpponent, 35.3%]
-
A.
firstRoundVoteShareWinnerPercentage
Indicates the percentage of total votes received by the winning candidate or option in the first round of voting.
-
B.
secondRoundVoteShareOf
Indicates the proportion of total votes an entity receives in the second round of a multi-round voting or election process.
-
C.
voteShareMainOpponent
chosen
Indicates the proportion of total votes received by the primary opposing candidate or party in an election.
-
D.
popularVoteCountOpponent
Indicates the number of votes received by the opposing candidate or party in a popular vote contest.
-
E.
firstRoundLeadingCandidate
Indicates that the subject is the candidate who is leading in vote count after the first round of an election or 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_69d86d9bf930819082b30cf6d169297c |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e04f932a248190b65ecfb2bc56e715 |
completed | April 16, 2026, 2:55 a.m. |
| PD | Predicate disambiguation | batch_69e00526759c819088b80d85138b8974 |
completed | April 15, 2026, 9:37 p.m. |
Created at: April 10, 2026, 4:45 a.m.