Triple
T7909708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agyness Deyn |
E183665
|
entity |
| Predicate | discoveredAsModel |
P25799
|
FINISHED |
| Object | in London while working in a fast-food restaurant |
—
|
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: in London while working in a fast-food restaurant | Statement: [Agyness Deyn, discoveredAsModel, in London while working in a fast-food restaurant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: discoveredAsModel Context triple: [Agyness Deyn, discoveredAsModel, in London while working in a fast-food restaurant]
-
A.
introducedAsModel
Indicates that one entity is presented or identified to others in the role or capacity of a model.
-
B.
discoveredAs
chosen
Indicates that one entity was first identified, found, or recognized in the role or form specified by another entity.
-
C.
discoveredAsPartOf
Indicates that something was found, identified, or revealed in the course of a larger activity, process, or investigation of which it formed a component.
-
D.
isModelOf
Indicates that one entity serves as a representation or abstraction that captures the structure or behavior of another entity.
-
E.
discoveredResource
Indicates that an entity has found, identified, or uncovered a particular resource.
- 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_69ca828dec0c81908b8f55a4dbbb53ff |
completed | March 30, 2026, 2:02 p.m. |
| NER | Named-entity recognition | batch_69cb3a5db9508190bbe92673ef5a7861 |
completed | March 31, 2026, 3:07 a.m. |
| PD | Predicate disambiguation | batch_69cae92f9498819085277879e59aa072 |
completed | March 30, 2026, 9:20 p.m. |
Created at: March 30, 2026, 5:04 p.m.