Triple

T27662476
Position Surface form Disambiguated ID Type / Status
Subject Bigtable: A Distributed Storage System for Structured Data E697155 entity
Predicate hasAuthor P4244 FINISHED
Object Murali Prabhakaran
Murali Prabhakaran is a computer scientist known for co-authoring Google's influential paper on Bigtable, a distributed storage system for structured data.
E1782779 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: Murali Prabhakaran | Statement: [Bigtable: A Distributed Storage System for Structured Data, hasAuthor, Murali Prabhakaran]
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: Murali Prabhakaran
Triple: [Bigtable: A Distributed Storage System for Structured Data, hasAuthor, Murali Prabhakaran]
Generated description
Murali Prabhakaran is a computer scientist known for co-authoring Google's influential paper on Bigtable, a distributed storage system for structured data.

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_69ef590b85a4819083ec7c12bd3c9c10 completed April 27, 2026, 12:39 p.m.
NER Named-entity recognition batch_69f634a183bc8190bdb59700f8f0a16e completed May 2, 2026, 5:30 p.m.
NED1 Entity disambiguation (via context triple) batch_6a12da9f469c819088ada806fbe51075 completed May 24, 2026, 11:01 a.m.
NEDg Description generation batch_6a12db41934c8190b860473fb4b6c979 completed May 24, 2026, 11:04 a.m.
NED2 Entity disambiguation (via description) batch_6a12dbcfd4588190a6b414466e5bc7cb completed May 24, 2026, 11:06 a.m.
Created at: April 27, 2026, 2:37 p.m.