Triple

T29580601
Position Surface form Disambiguated ID Type / Status
Subject Richard S. Sutton E753566 entity
Predicate notableWork P4 FINISHED
Object policy gradient theorem
The policy gradient theorem is a fundamental result in reinforcement learning that provides a way to compute the gradient of expected return with respect to policy parameters, enabling gradient-based optimization of stochastic policies.
 E1874121 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: policy gradient theorem | Statement: [Richard S. Sutton, notableWork, policy gradient theorem]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: policy gradient theorem
Triple: [Richard S. Sutton, notableWork, policy gradient theorem]
Generated description
The policy gradient theorem is a fundamental result in reinforcement learning that provides a way to compute the gradient of expected return with respect to policy parameters, enabling gradient-based optimization of stochastic policies.

Provenance (5 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_69f0ef80bf8c8190ad286e99f7df0c63 completed April 28, 2026, 5:33 p.m.
NER Named-entity recognition batch_69f66d78f2fc8190bc7def38615f2407 completed May 2, 2026, 9:32 p.m.
NED1 Entity disambiguation (via context triple) batch_6a262d74b2f88190a387a0cd7b506b03 completed June 8, 2026, 2:48 a.m.
NEDg Description generation batch_6a26318fba948190a7676b94a96e2385 completed June 8, 2026, 3:05 a.m.
NED2 Entity disambiguation (via description) batch_6a2635aebca08190bedcd6f2c3e9d58c completed June 8, 2026, 3:23 a.m.
Created at: April 28, 2026, 6:06 p.m.