Triple

T1996488
Position Surface form Disambiguated ID Type / Status
Subject British Geological Survey E43371 entity
Predicate abbreviation P43 FINISHED
Object BGS
BGS is the United Kingdom’s principal public-sector geoscience research organization, responsible for surveying, monitoring, and providing data on the nation’s geology and related Earth science hazards.
 E223347 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: BGS | Statement: [British Geological Survey, abbreviation, BGS]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BGS
Context triple: [British Geological Survey, abbreviation, BGS]
  • A. BnG
    BnG is the commonly used abbreviation for Bòrd na Gàidhlig, the principal public body responsible for promoting and supporting the Scottish Gaelic language in Scotland.
  • B. Boden
    Boden is a northern Swedish town known for its strategic military significance and large army garrison.
  • C. BG
    BG is the two-letter ISO 3166-1 alpha-2 country code representing Bulgaria.
  • D. Borrowash
    Borrowash is a large village in the county of Derbyshire, England, situated just east of the city of Derby.
  • E. Gabey
    Gabey is the enthusiastic sailor protagonist in the musical "On the Town," known for his romantic pursuit of Miss Turnstiles during a whirlwind 24-hour shore leave in New York City.
  • 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: BGS
Triple: [British Geological Survey, abbreviation, BGS]
Generated description
BGS is the United Kingdom’s principal public-sector geoscience research organization, responsible for surveying, monitoring, and providing data on the nation’s geology and related Earth science hazards.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BGS
Target entity description: BGS is the United Kingdom’s principal public-sector geoscience research organization, responsible for surveying, monitoring, and providing data on the nation’s geology and related Earth science hazards.
  • A. BnG
    BnG is the commonly used abbreviation for Bòrd na Gàidhlig, the principal public body responsible for promoting and supporting the Scottish Gaelic language in Scotland.
  • B. Boden
    Boden is a northern Swedish town known for its strategic military significance and large army garrison.
  • C. BG
    BG is the two-letter ISO 3166-1 alpha-2 country code representing Bulgaria.
  • D. Borrowash
    Borrowash is a large village in the county of Derbyshire, England, situated just east of the city of Derby.
  • E. Gabey
    Gabey is the enthusiastic sailor protagonist in the musical "On the Town," known for his romantic pursuit of Miss Turnstiles during a whirlwind 24-hour shore leave in New York City.
  • 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_69a88714cf2c819081644be450b8356e completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb8666b14819084374b84b65c6c74 completed March 7, 2026, 5:32 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae033e733c8190aa11e316e01dbd17 completed March 8, 2026, 11:16 p.m.
NEDg Description generation batch_69ae05c4c0b48190a2c063f991083ed9 completed March 8, 2026, 11:27 p.m.
NED2 Entity disambiguation (via description) batch_69ae0731c56081909849263e12750ad6 completed March 8, 2026, 11:33 p.m.
Created at: March 4, 2026, 7:37 p.m.