Triple

T15139338
Position Surface form Disambiguated ID Type / Status
Subject Hector Garcia-Molina E361642 entity
Predicate notableWork P4 FINISHED
Object Censorship-resistant publishing systems
Censorship-resistant publishing systems are distributed, fault-tolerant architectures designed to store and disseminate information in ways that make it extremely difficult for authorities or adversaries to suppress, alter, or remove published content.
E1139504 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: Censorship-resistant publishing systems | Statement: [Hector Garcia-Molina, notableWork, Censorship-resistant publishing systems]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Censorship-resistant publishing systems
Context triple: [Hector Garcia-Molina, notableWork, Censorship-resistant publishing systems]
  • A. Information Doesn’t Want to Be Free
    "Information Doesn’t Want to Be Free" is a nonfiction book by Cory Doctorow that critiques modern copyright and digital rights regimes while advocating for open culture and user freedoms in the digital age.
  • B. paper "Chaffing and Winnowing: Confidentiality without Encryption"
    "Chaffing and Winnowing: Confidentiality without Encryption" is a paper by Ronald L. Rivest that proposes a method for achieving data confidentiality without using traditional encryption, instead relying on message authentication codes and the separation of valid and invalid data.
  • C. Decentralized Administration of Attica
    The Decentralized Administration of Attica is a regional state authority in Greece responsible for overseeing and coordinating government functions across the Attica area, including municipalities such as Marathon.
  • D. Practical Byzantine Fault Tolerance
    Practical Byzantine Fault Tolerance is a consensus algorithm for distributed systems that efficiently tolerates Byzantine (arbitrary) faults, enabling reliable operation even when some nodes behave maliciously or unpredictably.
  • E. Blakley secret sharing scheme
    The Blakley secret sharing scheme is a threshold cryptographic method that hides a secret as the intersection point of multiple hyperplanes, requiring a minimum number of shares (hyperplanes) to reconstruct it.
  • 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: Censorship-resistant publishing systems
Triple: [Hector Garcia-Molina, notableWork, Censorship-resistant publishing systems]
Generated description
Censorship-resistant publishing systems are distributed, fault-tolerant architectures designed to store and disseminate information in ways that make it extremely difficult for authorities or adversaries to suppress, alter, or remove published content.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Censorship-resistant publishing systems
Target entity description: Censorship-resistant publishing systems are distributed, fault-tolerant architectures designed to store and disseminate information in ways that make it extremely difficult for authorities or adversaries to suppress, alter, or remove published content.
  • A. Information Doesn’t Want to Be Free
    "Information Doesn’t Want to Be Free" is a nonfiction book by Cory Doctorow that critiques modern copyright and digital rights regimes while advocating for open culture and user freedoms in the digital age.
  • B. paper "Chaffing and Winnowing: Confidentiality without Encryption"
    "Chaffing and Winnowing: Confidentiality without Encryption" is a paper by Ronald L. Rivest that proposes a method for achieving data confidentiality without using traditional encryption, instead relying on message authentication codes and the separation of valid and invalid data.
  • C. Decentralized Administration of Attica
    The Decentralized Administration of Attica is a regional state authority in Greece responsible for overseeing and coordinating government functions across the Attica area, including municipalities such as Marathon.
  • D. Practical Byzantine Fault Tolerance
    Practical Byzantine Fault Tolerance is a consensus algorithm for distributed systems that efficiently tolerates Byzantine (arbitrary) faults, enabling reliable operation even when some nodes behave maliciously or unpredictably.
  • E. Blakley secret sharing scheme
    The Blakley secret sharing scheme is a threshold cryptographic method that hides a secret as the intersection point of multiple hyperplanes, requiring a minimum number of shares (hyperplanes) to reconstruct it.
  • 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_69d85a06450081909c5a14ea9851a15e completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e005b59b488190b0016970647e7483 completed April 15, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69febfec3ae48190b2d8e853dab00777 completed May 9, 2026, 5:02 a.m.
NEDg Description generation batch_69fec0c97f4c819084ba9eb2d8f69ceb completed May 9, 2026, 5:06 a.m.
NED2 Entity disambiguation (via description) batch_69fec13ccea48190aeb155af012478b8 completed May 9, 2026, 5:08 a.m.
Created at: April 10, 2026, 3:07 a.m.