Triple
T241858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Kerry 2004 presidential campaign |
E4946
|
entity |
| Predicate | campaignStart |
P5415
|
FINISHED |
| Object | 2003 |
—
|
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: 2003 | Statement: [John Kerry 2004 presidential campaign, campaignStart, 2003]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: campaignStart Context triple: [John Kerry 2004 presidential campaign, campaignStart, 2003]
-
A.
campaignType
Indicates the specific category or kind of campaign an entity is associated with or participates in.
-
B.
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.
-
C.
campaignManager
Indicates that one entity serves as the manager or coordinator responsible for planning, executing, and overseeing a campaign on behalf of another entity.
-
D.
startOfMajorCampaign
chosen
Indicates that the referenced event marks the beginning of a significant, large-scale campaign or operation.
-
E.
campaignTheme
Indicates the central idea or message that characterizes and unifies a particular campaign.
- 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_69a257c3d0708190b0871c4269d273e6 |
completed | Feb. 28, 2026, 2:49 a.m. |
| NER | Named-entity recognition | batch_69a25d35aa288190966b6e15af1525cb |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b60ad308190b12f119960a8bde7 |
completed | Feb. 28, 2026, 3:05 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.