Triple
T579670
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Estonian language |
E15029
|
entity |
| Predicate | languageRegulator |
P6195
|
FINISHED |
| Object |
Institute of the Estonian Language
The Institute of the Estonian Language is Estonia’s central research and standardization body responsible for developing, preserving, and regulating the Estonian language.
|
E72593
|
NE FINISHED |
How this triple was built (5 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: Institute of the Estonian Language | Statement: [Estonian language, languageRegulator, Institute of the Estonian Language]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Institute of the Estonian Language Context triple: [Estonian language, languageRegulator, Institute of the Estonian Language]
-
A.
University of Tartu
The University of Tartu is a leading research-intensive university in Estonia, renowned for its strong programs in the humanities, natural and social sciences, and its historic role in Baltic and Nordic higher education.
-
B.
Institute for the Languages of Finland
The Institute for the Languages of Finland is a governmental research and expert body that develops, standardizes, and provides guidance on Finland’s national and minority languages.
-
C.
University of Tartu Library
The University of Tartu Library is the main academic library of the University of Tartu in Estonia, serving as a major national research and cultural repository.
-
D.
Akademio de Esperanto
Akademio de Esperanto is the official body that oversees the evolution, norms, and proper usage of the international language Esperanto.
-
E.
University of Tartu Museum
The University of Tartu Museum is a cultural and scientific museum in Tartu, Estonia, showcasing the history, heritage, and research legacy of the University of Tartu.
- 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: Institute of the Estonian Language Triple: [Estonian language, languageRegulator, Institute of the Estonian Language]
Generated description
The Institute of the Estonian Language is Estonia’s central research and standardization body responsible for developing, preserving, and regulating the Estonian language.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Institute of the Estonian Language Target entity description: The Institute of the Estonian Language is Estonia’s central research and standardization body responsible for developing, preserving, and regulating the Estonian language.
-
A.
University of Tartu
The University of Tartu is a leading research-intensive university in Estonia, renowned for its strong programs in the humanities, natural and social sciences, and its historic role in Baltic and Nordic higher education.
-
B.
Institute for the Languages of Finland
The Institute for the Languages of Finland is a governmental research and expert body that develops, standardizes, and provides guidance on Finland’s national and minority languages.
-
C.
University of Tartu Library
The University of Tartu Library is the main academic library of the University of Tartu in Estonia, serving as a major national research and cultural repository.
-
D.
Akademio de Esperanto
Akademio de Esperanto is the official body that oversees the evolution, norms, and proper usage of the international language Esperanto.
-
E.
University of Tartu Museum
The University of Tartu Museum is a cultural and scientific museum in Tartu, Estonia, showcasing the history, heritage, and research legacy of the University of Tartu.
- F. None of above. chosen
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: languageRegulator Context triple: [Estonian language, languageRegulator, Institute of the Estonian Language]
-
A.
languageShift
Indicates a change in the primary language used by an entity, such as switching from one language to another over time or in a given context.
-
B.
languageProvision
Indicates that one entity supplies, supports, or makes available a particular language (or set of languages) for use by another entity.
-
C.
languageStandard
chosen
Indicates that one entity conforms to, is defined by, or is governed by the language rules, specifications, or conventions established by another entity as a standard.
-
D.
languageForm
Indicates the specific linguistic form or expression in which something is conveyed or represented.
-
E.
lexifierLanguage
Indicates that one language serves as the primary source or base language from which the core vocabulary and structure of another language, typically a pidgin or creole, are derived.
- F. None of above.
Provenance (6 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_69a4935783b8819082b77726ec10cc42 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b6c358081908f458b9e3e208c0d |
completed | March 1, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a501c1b8448190847197d984f211c3 |
completed | March 2, 2026, 3:19 a.m. |
| NEDg | Description generation | batch_69a503b501388190baed19e781c24b4d |
completed | March 2, 2026, 3:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a5077cf14081909478ea1e0fd3eff5 |
completed | March 2, 2026, 3:43 a.m. |
| PD | Predicate disambiguation | batch_69a494c692288190b88f30299516b5ba |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.