Triple

T816975
Position Surface form Disambiguated ID Type / Status
Subject PostgreSQL E17669 entity
Predicate supportsIndexType P203 FINISHED
Object BRIN
BRIN (Block Range Index) is a lightweight PostgreSQL index type optimized for very large tables by summarizing ranges of physical data blocks instead of indexing every individual row.
 E97114 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: BRIN | Statement: [PostgreSQL, supportsIndexType, BRIN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BRIN
Context triple: [PostgreSQL, supportsIndexType, BRIN]
  • A. Brin
    Brin is a surname most prominently associated with Sergey Brin, the co-founder of Google and a leading figure in the technology industry.
  • B. BR
    BR is the upper house of Austria’s parliament, representing the federal states in the legislative process.
  • C. BR2
    BR2 is a UK postcode district covering parts of Hayes and surrounding areas in the London Borough of Bromley in southeast England.
  • D. Bing
    Bing is Microsoft's web search engine that provides internet search, image, video, and mapping services.
  • E. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • 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: BRIN
Triple: [PostgreSQL, supportsIndexType, BRIN]
Generated description
BRIN (Block Range Index) is a lightweight PostgreSQL index type optimized for very large tables by summarizing ranges of physical data blocks instead of indexing every individual row.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BRIN
Target entity description: BRIN (Block Range Index) is a lightweight PostgreSQL index type optimized for very large tables by summarizing ranges of physical data blocks instead of indexing every individual row.
  • A. Brin
    Brin is a surname most prominently associated with Sergey Brin, the co-founder of Google and a leading figure in the technology industry.
  • B. BR
    BR is the upper house of Austria’s parliament, representing the federal states in the legislative process.
  • C. BR2
    BR2 is a UK postcode district covering parts of Hayes and surrounding areas in the London Borough of Bromley in southeast England.
  • D. Bing
    Bing is Microsoft's web search engine that provides internet search, image, video, and mapping services.
  • E. BdM
    BdM is the central bank of Mexico, responsible for maintaining the country’s monetary stability and issuing its currency.
  • 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_69a4937bcaac8190a322524ac6f45a5a completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a4b2b503d48190bd4f33548a22d5fe completed March 1, 2026, 9:42 p.m.
NED1 Entity disambiguation (via context triple) batch_69a76d8d1a448190be8494fa2776615a completed March 3, 2026, 11:23 p.m.
NEDg Description generation batch_69a78bd0a1d48190907434a17853dfb1 completed March 4, 2026, 1:33 a.m.
NED2 Entity disambiguation (via description) batch_69a78c3a57d88190a994ed44bcb2d8d1 completed March 4, 2026, 1:34 a.m.
Created at: March 1, 2026, 7:38 p.m.