Triple
T14470728
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Johann Heinrich von Thünen Institute facilities |
E358832
|
entity |
| Predicate | affiliation |
P10
|
FINISHED |
| Object |
German federal research institutions network
The German federal research institutions network is a coordinated system of government-funded scientific organizations in Germany that conduct applied and policy-relevant research across diverse fields to support national decision-making and innovation.
|
E1101298
|
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: German federal research institutions network | Statement: [Johann Heinrich von Thünen Institute facilities, affiliation, German federal research institutions network]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: German federal research institutions network Context triple: [Johann Heinrich von Thünen Institute facilities, affiliation, German federal research institutions network]
-
A.
Berlin-Brandenburg research networks
Berlin-Brandenburg research networks are collaborative scientific alliances in the Berlin-Brandenburg region that connect universities, research institutes, and other partners to advance interdisciplinary research and innovation.
-
B.
Helmholtz Association
The Helmholtz Association is Germany’s largest scientific research organization, operating a network of national research centers that conduct long-term, large-scale research in areas such as energy, health, environment, and technology.
-
C.
German astronomical research network
The German astronomical research network is a collaborative national framework that coordinates and supports astronomy and astrophysics research across multiple observatories and institutes in Germany.
-
D.
German Research Foundation
The German Research Foundation is Germany’s central self-governing research funding organization, supporting research projects and infrastructure across all disciplines at universities and research institutions.
-
E.
German Universities of Technology network
The German Universities of Technology network is an alliance of leading German technical universities that collaborate on research, teaching, and innovation in engineering and the applied sciences.
- 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: German federal research institutions network Triple: [Johann Heinrich von Thünen Institute facilities, affiliation, German federal research institutions network]
Generated description
The German federal research institutions network is a coordinated system of government-funded scientific organizations in Germany that conduct applied and policy-relevant research across diverse fields to support national decision-making and innovation.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: German federal research institutions network Target entity description: The German federal research institutions network is a coordinated system of government-funded scientific organizations in Germany that conduct applied and policy-relevant research across diverse fields to support national decision-making and innovation.
-
A.
Berlin-Brandenburg research networks
Berlin-Brandenburg research networks are collaborative scientific alliances in the Berlin-Brandenburg region that connect universities, research institutes, and other partners to advance interdisciplinary research and innovation.
-
B.
Helmholtz Association
The Helmholtz Association is Germany’s largest scientific research organization, operating a network of national research centers that conduct long-term, large-scale research in areas such as energy, health, environment, and technology.
-
C.
German astronomical research network
The German astronomical research network is a collaborative national framework that coordinates and supports astronomy and astrophysics research across multiple observatories and institutes in Germany.
-
D.
German Research Foundation
The German Research Foundation is Germany’s central self-governing research funding organization, supporting research projects and infrastructure across all disciplines at universities and research institutions.
-
E.
German Universities of Technology network
The German Universities of Technology network is an alliance of leading German technical universities that collaborate on research, teaching, and innovation in engineering and the applied sciences.
- 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_69d827966698819082e140837737501d |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de91f969788190a5114f92d7159aae |
completed | April 14, 2026, 7:14 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd649beec88190861abb52c5a2733e |
completed | May 8, 2026, 4:20 a.m. |
| NEDg | Description generation | batch_69fd67b1ed2081908d3de6514078be49 |
completed | May 8, 2026, 4:33 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fd682f28948190adc037c18c7deb93 |
completed | May 8, 2026, 4:35 a.m. |
Created at: April 10, 2026, 1:20 a.m.