Triple
T1659667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vote Leave |
E35875
|
entity |
| Predicate | usedCampaignBus |
P2543
|
FINISHED |
| Object | red campaign bus with NHS funding claim |
—
|
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: red campaign bus with NHS funding claim | Statement: [Vote Leave, usedCampaignBus, red campaign bus with NHS funding claim]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usedCampaignBus Context triple: [Vote Leave, usedCampaignBus, red campaign bus with NHS funding claim]
-
A.
testCampaign
Indicates that an entity is involved in or associated with a campaign conducted for testing, experimentation, or evaluation purposes.
-
B.
campaignType
Indicates the specific category or kind of campaign an entity is associated with or participates in.
-
C.
partOfCampaign
chosen
Indicates that an entity participates in, belongs to, or is included within a specific campaign.
-
D.
ledCampaignIn
Indicates that an entity directed or was in charge of organizing and executing a campaign within a particular context or location.
-
E.
effectOnCampaign
Indicates the influence or impact that one factor has on the outcome or performance of a 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_69a88606aa808190aa0b421b4271f220 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aaf3359ce48190803b322db8ad6027 |
completed | March 6, 2026, 3:31 p.m. |
| PD | Predicate disambiguation | batch_69a907cff53c8190b424f088478d3e2c |
completed | March 5, 2026, 4:34 a.m. |
Created at: March 4, 2026, 7:29 p.m.