Triple

T18301068
Position Surface form Disambiguated ID Type / Status
Subject Optax E438357 entity
Predicate providesOptimizer P56342 FINISHED
Object adafactor
Adafactor is an adaptive, memory-efficient optimization algorithm commonly used to train large-scale neural networks, particularly in natural language processing models.
 E1317501 NE FINISHED

How this triple was built (4 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: adafactor | Statement: [Optax, providesOptimizer, adafactor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: adafactor
Context triple: [Optax, providesOptimizer, adafactor]
  • A. ADAV
    ADAV was the abbreviation for the General German Workers' Association, one of the first major socialist workers' parties in 19th-century Germany.
  • B. Apado
    Apado is a town and local settlement located within the Ilorin East area of Kwara State, Nigeria.
  • C. FAF
    FAF is the commonly used abbreviation for the Financial Accounting Foundation, the U.S. organization that oversees and supports the creation of financial accounting and reporting standards.
  • D. FAF
    FAF is the governing body responsible for overseeing and organizing football activities and competitions in Algeria.
  • E. ADF
    ADF is the abbreviation for the European Parliament’s Committee on Foreign Affairs, which focuses on the EU’s external relations, trade policy, and development cooperation.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: adafactor
Triple: [Optax, providesOptimizer, adafactor]
Generated description
Adafactor is an adaptive, memory-efficient optimization algorithm commonly used to train large-scale neural networks, particularly in natural language processing models.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: adafactor
Target entity description: Adafactor is an adaptive, memory-efficient optimization algorithm commonly used to train large-scale neural networks, particularly in natural language processing models.
  • A. ADAV
    ADAV was the abbreviation for the General German Workers' Association, one of the first major socialist workers' parties in 19th-century Germany.
  • B. Apado
    Apado is a town and local settlement located within the Ilorin East area of Kwara State, Nigeria.
  • C. FAF
    FAF is the commonly used abbreviation for the Financial Accounting Foundation, the U.S. organization that oversees and supports the creation of financial accounting and reporting standards.
  • D. FAF
    FAF is the governing body responsible for overseeing and organizing football activities and competitions in Algeria.
  • E. ADF
    ADF is the abbreviation for the European Parliament’s Committee on Foreign Affairs, which focuses on the EU’s external relations, trade policy, and development cooperation.
  • F. None of above. chosen

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_69d8b915e3e881909125d760c15d0c29 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e5017f63dc819083a675d570620f2f completed April 19, 2026, 4:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03bb5e1fb481908a0b98ea130eda71 completed May 12, 2026, 11:44 p.m.
NEDg Description generation batch_6a03bdb3fb3c819095192ac49e809f55 completed May 12, 2026, 11:54 p.m.
NED2 Entity disambiguation (via description) batch_6a03c193a0a08190b33d80d45f3ed0f0 completed May 13, 2026, 12:10 a.m.
Created at: April 10, 2026, 10:35 a.m.