Triple

T19619447
Position Surface form Disambiguated ID Type / Status
Subject Rob Fergus E470958 entity
Predicate doctoralAdvisor P167 FINISHED
Object Andrew Zisserman NE NERFINISHED

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: Andrew Zisserman | Statement: [Rob Fergus, doctoralAdvisor, Andrew Zisserman]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Andrew Zisserman
Context triple: [Rob Fergus, doctoralAdvisor, Andrew Zisserman]
  • A. Andrew Zisserman chosen
    Andrew Zisserman is a prominent British computer vision researcher and professor known for foundational contributions to object recognition, image understanding, and influential deep learning architectures.
  • B. Andrea Vedaldi
    Andrea Vedaldi is a computer vision researcher and professor known for his contributions to visual recognition, image understanding, and deep learning methods.
  • C. 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.
  • D. Alexei Efros
    Alexei Efros is a prominent computer scientist known for his influential work in computer vision and computational photography.
  • E. Karen Simonyan
    Karen Simonyan is a computer scientist and deep learning researcher known for influential work in neural network architectures and generative models, including contributions to systems like WaveNet.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e510fa248190b7afb274a1d4cf73 completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640e4570c81909fc4f9b871346337 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:43 p.m.