Triple

T18872709
Position Surface form Disambiguated ID Type / Status
Subject EFTA Surveillance Authority E461610 entity
Predicate shortName P43 FINISHED
Object ESA
ESA is the EFTA Surveillance Authority, the body responsible for monitoring compliance with European Economic Area rules in the EFTA states.
E1346962 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: ESA | Statement: [EFTA Surveillance Authority, shortName, ESA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: ESA
Context triple: [EFTA Surveillance Authority, shortName, ESA]
  • A. ESA
    ESA is a major professional organization dedicated to advancing the science and practice of ecology.
  • B. ESA
    ESA is a renowned independent architecture school in Paris known for its innovative and experimental approach to architectural education.
  • C. ESA
    ESA is the abbreviation for the Eight Schools Association, a collaborative group of prestigious New England boarding schools.
  • D. ESA
    ESA is a professional scientific society dedicated to the study of insects and the advancement of entomological science.
  • E. ESA
    ESA is a landmark U.S. environmental law that provides for the conservation and protection of threatened and endangered plant and animal species and their habitats.
  • 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: ESA
Triple: [EFTA Surveillance Authority, shortName, ESA]
Generated description
ESA is the EFTA Surveillance Authority, the body responsible for monitoring compliance with European Economic Area rules in the EFTA states.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: ESA
Target entity description: ESA is the EFTA Surveillance Authority, the body responsible for monitoring compliance with European Economic Area rules in the EFTA states.
  • A. ESA
    ESA (European Space Agency) is an intergovernmental organization dedicated to space exploration, science, and technology development on behalf of its European member states.
  • B. ESA
    ESA is the standardized European Union framework for collecting, organizing, and presenting national and regional economic statistics.
  • C. ESA
    ESA is a major professional organization dedicated to advancing the science and practice of ecology.
  • D. ESA
    ESA is the abbreviation for the Eight Schools Association, a collaborative group of prestigious New England boarding schools.
  • E. ESA
    ESA is a professional scientific society dedicated to the study of insects and the advancement of entomological science.
  • 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_69d8dcfb7b9c8190854e7b171b98ea2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5c2aa9074819092137d236df3717b completed April 20, 2026, 6:07 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0575bd2ee48190ab4474a85385c551 completed May 14, 2026, 7:11 a.m.
NEDg Description generation batch_6a05796169a4819094b37d22dc9cb39a completed May 14, 2026, 7:27 a.m.
NED2 Entity disambiguation (via description) batch_6a0579d6b0d48190a5d7afb334cb3658 completed May 14, 2026, 7:29 a.m.
Created at: April 10, 2026, 11:57 a.m.