Triple
T2766230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | United States federal elections |
E61344
|
entity |
| Predicate | Election Day |
P9219
|
FINISHED |
| Object | Tuesday after the first Monday in November |
—
|
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: Tuesday after the first Monday in November | Statement: [United States federal elections, Election Day, Tuesday after the first Monday in November]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Election Day Context triple: [United States federal elections, Election Day, Tuesday after the first Monday in November]
-
A.
electionDate
chosen
Indicates the specific calendar date on which an election is scheduled to be or was held.
-
B.
electionHeldIn
Indicates that an election event took place within a specific geographic or political location.
-
C.
electionCalledDate
Indicates the date on which an election is officially announced or formally called.
-
D.
electoralCollegeVoteDate
Indicates the date on which Electoral College votes are formally cast for a given election.
-
E.
presidentialVote
Indicates that an entity casts or records a vote in a presidential election for a particular candidate or option.
- 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_69ab4b7bab6c8190a5c2efef19a8ef34 |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abddceb9d88190961e30d521a21552 |
completed | March 7, 2026, 8:11 a.m. |
| PD | Predicate disambiguation | batch_69abdcfc5e1c8190a5ac2c48d3eaeb0a |
completed | March 7, 2026, 8:08 a.m. |
Created at: March 6, 2026, 9:57 p.m.