Triple

T21023065
Position Surface form Disambiguated ID Type / Status
Subject Southern Avenue SE E517863 entity
Predicate hasAbbreviation P43 FINISHED
Object SE
SE is a common abbreviation used in addresses to denote the southeast quadrant or section of a city or area.
 E1462256 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: SE | Statement: [Southern Avenue SE, hasAbbreviation, SE]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: SE
Context triple: [Southern Avenue SE, hasAbbreviation, SE]
  • A. SE
    SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
  • B. SE
    SE is the official two-letter postal abbreviation for the Brazilian state of Sergipe.
  • C. SE
    SE is the standard abbreviation for a Societas Europaea, a public limited-liability company structure that allows firms to operate across European Union member states under a single legal form.
  • D. SE
    SE is the commonly used abbreviation for Mexico’s Secretariat of Economy, the federal government ministry responsible for economic policy, trade, and industrial development.
  • E. SE
    SE is the New York Stock Exchange ticker symbol for Sea Limited, a Singapore-based global consumer internet company known for its e-commerce, digital entertainment, and financial services platforms.
  • 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: SE
Triple: [Southern Avenue SE, hasAbbreviation, SE]
Generated description
SE is a common abbreviation used in addresses to denote the southeast quadrant or section of a city or area.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: SE
Target entity description: SE is a common abbreviation used in addresses to denote the southeast quadrant or section of a city or area.
  • A. SE
    SE is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Sweden in international standards and systems.
  • B. SE
    SE is the official two-letter postal abbreviation for the Brazilian state of Sergipe.
  • C. SE
    SE is the standard abbreviation for a Societas Europaea, a public limited-liability company structure that allows firms to operate across European Union member states under a single legal form.
  • D. SE
    SE is the commonly used abbreviation for Mexico’s Secretariat of Economy, the federal government ministry responsible for economic policy, trade, and industrial development.
  • E. SE
    SE is the New York Stock Exchange ticker symbol for Sea Limited, a Singapore-based global consumer internet company known for its e-commerce, digital entertainment, and financial services platforms.
  • 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_69e0b50262b081909bc488937145eb73 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fc5e85d08190a67956a3dbe693de completed April 21, 2026, 4:26 a.m.
NED1 Entity disambiguation (via context triple) batch_6a093b68fd48819098ba4ba22a4f1cbd completed May 17, 2026, 3:52 a.m.
NEDg Description generation batch_6a093d26c38881908f8e5e0200411330 completed May 17, 2026, 3:59 a.m.
NED2 Entity disambiguation (via description) batch_6a093da7c214819099218effbfba8ac7 completed May 17, 2026, 4:01 a.m.
Created at: April 16, 2026, 1:55 p.m.