Triple

T18528268

Position	Surface form	Disambiguated ID	Type / Status
Subject	Facebook Engineering	`E452772`	entity
Predicate	developedTechnology	`P5334`	FINISHED
Object	Facebook’s News Feed ranking systems Facebook’s News Feed ranking systems are the machine-learning–driven algorithms that determine which posts and updates users see and in what order on the Facebook platform.	`E1328935`	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: Facebook’s News Feed ranking systems | Statement: [Facebook Engineering, developedTechnology, Facebook’s News Feed ranking systems]

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: Facebook’s News Feed ranking systems
Context triple: [Facebook Engineering, developedTechnology, Facebook’s News Feed ranking systems]

A. Networks, Crowds, and Markets: Reasoning About a Highly Connected World
"Networks, Crowds, and Markets: Reasoning About a Highly Connected World" is an interdisciplinary textbook that introduces the mathematical and conceptual foundations of network science, game theory, and market dynamics in complex social and economic systems.
B. Recommender Systems: The Textbook
Recommender Systems: The Textbook is a comprehensive academic book by Charu C. Aggarwal that systematically covers the theory, algorithms, and practical applications of modern recommender systems.
C. The Facebook Effect
The Facebook Effect is a nonfiction book by David Kirkpatrick that chronicles the founding, growth, and global impact of Facebook on technology, business, and society.
D. Whuffie
Whuffie is a fictional reputation-based currency that measures social capital and replaces money in Cory Doctorow’s science fiction novel "Down and Out in the Magic Kingdom."
E. Building Social Business
"Building Social Business" is a book by Nobel laureate Muhammad Yunus that outlines the concept and practice of businesses designed primarily to solve social problems rather than maximize profit.
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: Facebook’s News Feed ranking systems
Triple: [Facebook Engineering, developedTechnology, Facebook’s News Feed ranking systems]

Generated description

Facebook’s News Feed ranking systems are the machine-learning–driven algorithms that determine which posts and updates users see and in what order on the Facebook platform.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: Facebook’s News Feed ranking systems
Target entity description: Facebook’s News Feed ranking systems are the machine-learning–driven algorithms that determine which posts and updates users see and in what order on the Facebook platform.

A. Networks, Crowds, and Markets: Reasoning About a Highly Connected World
"Networks, Crowds, and Markets: Reasoning About a Highly Connected World" is an interdisciplinary textbook that introduces the mathematical and conceptual foundations of network science, game theory, and market dynamics in complex social and economic systems.
B. Recommender Systems: The Textbook
Recommender Systems: The Textbook is a comprehensive academic book by Charu C. Aggarwal that systematically covers the theory, algorithms, and practical applications of modern recommender systems.
C. The Facebook Effect
The Facebook Effect is a nonfiction book by David Kirkpatrick that chronicles the founding, growth, and global impact of Facebook on technology, business, and society.
D. Whuffie
Whuffie is a fictional reputation-based currency that measures social capital and replaces money in Cory Doctorow’s science fiction novel "Down and Out in the Magic Kingdom."
E. Building Social Business
"Building Social Business" is a book by Nobel laureate Muhammad Yunus that outlines the concept and practice of businesses designed primarily to solve social problems rather than maximize profit.
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_69d8d387b5548190aa030dad2cb4947e`	completed	April 10, 2026, 10:40 a.m.
NER	Named-entity recognition	`batch_69e533fad2d081908395914d6a6b4eb1`	completed	April 19, 2026, 7:58 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a049178ea1c819085480137adfb3841`	completed	May 13, 2026, 2:58 p.m.
NEDg	Description generation	`batch_6a04921b1a508190b8bb6d6c4597ab99`	completed	May 13, 2026, 3 p.m.
NED2	Entity disambiguation (via description)	`batch_6a0492ba4ea08190b59510b221ad5d21`	completed	May 13, 2026, 3:03 p.m.

Created at: April 10, 2026, 11:37 a.m.