Triple

T13182786
Position Surface form Disambiguated ID Type / Status
Subject Bulgarian Academy of Sciences E313770 entity
Predicate shortName P43 FINISHED
Object BAN
BAN is the principal scientific organization in Bulgaria, encompassing a wide network of research institutes across various fields.
 E1026929 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: BAN | Statement: [Bulgarian Academy of Sciences, shortName, BAN]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: BAN
Context triple: [Bulgarian Academy of Sciences, shortName, BAN]
  • A. BAN
    BAN is the National Rail station code for Banbury railway station in Oxfordshire, England.
  • B. Ban
    Ban was the nickname of Ban Johnson, the influential early 20th-century baseball executive who served as the first president of the American League.
  • C. Ban
    Ban was a medieval noble title used in several Central and Southeast European states, often designating a high-ranking governor or viceroy.
  • D. Bann
    Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
  • E. Banning
    Banning is a small city in Southern California known for its location along the I-10 corridor between Los Angeles and Palm Springs.
  • 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: BAN
Triple: [Bulgarian Academy of Sciences, shortName, BAN]
Generated description
BAN is the principal scientific organization in Bulgaria, encompassing a wide network of research institutes across various fields.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: BAN
Target entity description: BAN is the principal scientific organization in Bulgaria, encompassing a wide network of research institutes across various fields.
  • A. BAN
    BAN is the National Rail station code for Banbury railway station in Oxfordshire, England.
  • B. Ban
    Ban was the nickname of Ban Johnson, the influential early 20th-century baseball executive who served as the first president of the American League.
  • C. Ban
    Ban was a medieval noble title used in several Central and Southeast European states, often designating a high-ranking governor or viceroy.
  • D. Bann
    Bann is an alternative name for the River Bann, one of the longest and most significant rivers in Northern Ireland.
  • E. Banning
    Banning is a small city in Southern California known for its location along the I-10 corridor between Los Angeles and Palm Springs.
  • 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_69d806ae1e08819090d95bfe1538cc17 completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d98c4a0b0081908027bf77442ff5ff completed April 10, 2026, 11:48 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6f5f307408190afd0df16a417c456 completed May 3, 2026, 7:14 a.m.
NEDg Description generation batch_69f6f707d9e48190b772520ca9f4ac2c completed May 3, 2026, 7:19 a.m.
NED2 Entity disambiguation (via description) batch_69f6f85149cc8190adf68387475d3286 completed May 3, 2026, 7:25 a.m.
Created at: April 9, 2026, 9:15 p.m.