Triple
T36242696
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deva Cassel |
E891567
|
entity |
| Predicate | wasFaceOfCampaign |
P184797
|
FINISHED |
| Object | Dolce & Gabbana fragrance 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: Dolce & Gabbana fragrance campaign | Statement: [Deva Cassel, wasFaceOfCampaign, Dolce & Gabbana fragrance campaign]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasFaceOfCampaign Context triple: [Deva Cassel, wasFaceOfCampaign, Dolce & Gabbana fragrance campaign]
-
A.
wasCandidateIn
Indicates that an entity served as a candidate in a particular election, contest, or selection process.
-
B.
servedInCampaign
Indicates that an individual participated in and rendered service during a specific military or organizational campaign.
-
C.
headOfGovernmentDuringCampaign
Indicates that an individual serves as the head of government for a given political entity during the period of an electoral campaign.
-
D.
wasOnBallotIn
Indicates that a candidate or option appeared as a choice on the official ballot in a specified election or voting event.
-
E.
hasPoliticalImage
Indicates that an entity is associated with or portrayed through a political image, representation, or visual symbol.
- F. None of above. chosen
Provenance (4 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_69f76e44993481908fa75e4c48d0aab3 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b5f89c5c8190825ed5d4317c540c |
completed | May 3, 2026, 8:54 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c44390819084fb5558b354658f |
completed | May 3, 2026, 8:49 p.m. |
| PDg | Predicate description generation | batch_69f7b57aa0848190a22c31c3ff90e0ab |
completed | May 3, 2026, 8:52 p.m. |
Created at: May 3, 2026, 4:09 p.m.