Triple
T33328008
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Presidency of John Tyler |
E853318
|
entity |
| Predicate | politicalPartyOfPresidentAtElection |
P39929
|
FINISHED |
| Object | Whig Party |
—
|
NE NERFINISHED |
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: Whig Party | Statement: [Presidency of John Tyler, politicalPartyOfPresidentAtElection, Whig Party]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: politicalPartyOfPresidentAtElection Context triple: [Presidency of John Tyler, politicalPartyOfPresidentAtElection, Whig Party]
-
A.
partyOfElectedPresident
Indicates the political party to which an elected president belongs.
-
B.
partyOfPresidentDuringTerm
chosen
Indicates the political party with which a president is affiliated during a specific term in office.
-
C.
rulingPartyDuringElection
Indicates that a specified political party was the official ruling party at the time a particular election took place.
-
D.
presidentPartyAtTime
Indicates that a specified person holds the office of president at a given time and is affiliated with a particular political party during that time.
-
E.
winnerPresidentialParty
Indicates that the specified political party is the party of the candidate who won a given presidential election.
- 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_69f34969614c81909cd99661b0902533 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fe163a41a0819098403b470e327d29 |
completed | May 8, 2026, 4:58 p.m. |
| PD | Predicate disambiguation | batch_69fe1358db5c819092570814a37ef5bd |
completed | May 8, 2026, 4:46 p.m. |
Created at: May 1, 2026, 1:34 a.m.