Triple
T921667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Christian Szegedy |
E19896
|
entity |
| Predicate | hasCitationImpactOn |
P13420
|
FINISHED |
| Object | ImageNet image classification |
—
|
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: ImageNet image classification | Statement: [Christian Szegedy, hasCitationImpactOn, ImageNet image classification]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCitationImpactOn Context triple: [Christian Szegedy, hasCitationImpactOn, ImageNet image classification]
-
A.
hasCitationImpact
chosen
Indicates that one entity (such as a publication, author, or venue) exerts measurable influence on scholarly work through citations it receives or generates.
-
B.
citesAs
Indicates that one entity references or acknowledges another as a source of information, authority, or evidence.
-
C.
stillCitedFor
Indicates that a work or source continues to be referenced or relied upon as a citation after its original publication or use.
-
D.
citationBy
Indicates that one work is cited or referenced by another work.
-
E.
citationNumber
Indicates the specific numeric identifier assigned to a citation within a document or reference list.
- 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_69a493a099788190a696d9d8408cbaf4 |
completed | March 1, 2026, 7:29 p.m. |
| NER | Named-entity recognition | batch_69a4b313cb908190ad78b3a54e4f2eb7 |
completed | March 1, 2026, 9:43 p.m. |
| PD | Predicate disambiguation | batch_69a4b295b02481908e5f53bfcb83cc94 |
completed | March 1, 2026, 9:41 p.m. |
Created at: March 1, 2026, 7:40 p.m.