Triple
T25791727
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Pitt Kellogg |
E649563
|
entity |
| Predicate | electionDisputedBy |
P50503
|
FINISHED |
| Object | Democratic Party in Louisiana |
—
|
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: Democratic Party in Louisiana | Statement: [William Pitt Kellogg, electionDisputedBy, Democratic Party in Louisiana]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: electionDisputedBy Context triple: [William Pitt Kellogg, electionDisputedBy, Democratic Party in Louisiana]
-
A.
hasOfficeContested
Indicates that an individual has been a candidate for a particular public office in an election.
-
B.
electionYearInDispute
Indicates that the specified election year is contested or under dispute regarding its legitimacy, outcome, or related circumstances.
-
C.
areContestedIn
Indicates that something is the subject of dispute, challenge, or competition within a particular context, event, or process.
-
D.
wasContestedBetween
chosen
Indicates that an event, position, or resource was the subject of competition or dispute involving two or more opposing parties.
-
E.
wasContestedIn
Indicates that an event, position, or decision was the subject of competition, dispute, or challenge within a particular context or proceeding.
- 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_69e7ab33e9308190afe415dc6f9e8876 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f6bbf6e33c819086e5176d64e7a614 |
completed | May 3, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69f6ba6b1e6c8190adf9d6a257e0b744 |
completed | May 3, 2026, 3 a.m. |
Created at: April 22, 2026, 6 a.m.