Triple
T8974575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jeanne Shaheen 2008 U.S. Senate campaign |
E214353
|
entity |
| Predicate | campaignClassification |
P672
|
FINISHED |
| Object | statewide campaign |
—
|
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: statewide campaign | Statement: [Jeanne Shaheen 2008 U.S. Senate campaign, campaignClassification, statewide campaign]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignClassification Context triple: [Jeanne Shaheen 2008 U.S. Senate campaign, campaignClassification, statewide campaign]
-
A.
campaignType
chosen
Indicates the specific category or kind of campaign an entity is associated with or participates in.
-
B.
classificationChange
Indicates a change in the category, type, or status under which an entity is classified.
-
C.
campaignSpecific
Indicates that something is restricted or tailored to a particular campaign, rather than being general or shared across multiple campaigns.
-
D.
classificationStart
Indicates the point in time or process at which a classification or categorization of an entity begins.
-
E.
campaign
Indicates that an entity actively organizes or conducts a coordinated effort or series of actions aimed at achieving a specific goal, often in political, commercial, or social contexts.
- 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_69ca839dbf608190a2f5990477115d29 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc6783abe48190840e652fc2acf28f |
completed | April 1, 2026, 12:32 a.m. |
| PD | Predicate disambiguation | batch_69cc5ed9a2d48190ad11381078e823b7 |
completed | March 31, 2026, 11:55 p.m. |
Created at: March 30, 2026, 7:02 p.m.