Triple
T15361415
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ResNeXt |
E367297
|
entity |
| Predicate | paperAuthors |
P2002
|
FINISHED |
| Object | Ross Girshick |
E1153669
|
NE 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: Ross Girshick | Statement: [ResNeXt, paperAuthors, Ross Girshick]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ross Girshick Context triple: [ResNeXt, paperAuthors, Ross Girshick]
-
A.
Ross Girshick
chosen
Ross Girshick is a computer vision researcher best known for pioneering the R-CNN family of deep learning models for object detection.
-
B.
Abraham Girshick
Abraham Girshick was an American statistician known for his contributions to statistical decision theory and his work during World War II with Columbia University's Statistical Research Group.
-
C.
Dario Amodei
Dario Amodei is an AI researcher and entrepreneur, co-founder and CEO of Anthropic and former OpenAI research leader known for his work on large language models and AI safety.
-
D.
Martin Hinton
Martin Hinton is a notable individual recognized for sharing the surname associated with the Hinton family name.
-
E.
Mark Dredze
Mark Dredze is a computer scientist and researcher known for his work in natural language processing, machine learning, and applications of AI to public health and social media analysis.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d85a1483788190ad93c2748e8af34b |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e03e4607408190ab281a7f7a8012d3 |
completed | April 16, 2026, 1:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff1343862481908962dfe0ab946b97 |
completed | May 9, 2026, 10:58 a.m. |
Created at: April 10, 2026, 3:18 a.m.