Triple
T2141655
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fraunhofer Society |
E46771
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object |
Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE
The Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE is a German applied research institute specializing in secure communication, sensor and information systems, and human–machine interaction, primarily for defense and security applications.
|
E236606
|
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: Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE | Statement: [Fraunhofer Society, hasPart, Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE Context triple: [Fraunhofer Society, hasPart, Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE]
-
A.
Fraunhofer Society
The Fraunhofer Society is a leading German organization for applied research, operating numerous institutes that develop practical innovations and technologies for industry and society.
-
B.
Max Planck Institute for Intelligent Systems
The Max Planck Institute for Intelligent Systems is a leading German research institute focused on advancing the understanding and development of intelligent systems, including machine learning, robotics, and related fields.
-
C.
Institute of Electronics and Telecommunications
The Institute of Electronics and Telecommunications is a specialized research and academic unit at Hanoi University of Science and Technology focusing on electronics, communications, and related technologies.
-
D.
Max Planck Institute for Informatics
The Max Planck Institute for Informatics is a leading German research institute specializing in computer science, particularly algorithms, data science, and artificial intelligence.
-
E.
Institute of Electronics, Communications and Information Technology
The Institute of Electronics, Communications and Information Technology is a research and innovation center at Queen’s University Belfast focused on advanced electronics, telecommunications, and information technologies.
- 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: Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE Triple: [Fraunhofer Society, hasPart, Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE]
Generated description
The Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE is a German applied research institute specializing in secure communication, sensor and information systems, and human–machine interaction, primarily for defense and security applications.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE Target entity description: The Fraunhofer Institute for Communication, Information Processing and Ergonomics FKIE is a German applied research institute specializing in secure communication, sensor and information systems, and human–machine interaction, primarily for defense and security applications.
-
A.
Fraunhofer Society
The Fraunhofer Society is a leading German organization for applied research, operating numerous institutes that develop practical innovations and technologies for industry and society.
-
B.
Max Planck Institute for Intelligent Systems
The Max Planck Institute for Intelligent Systems is a leading German research institute focused on advancing the understanding and development of intelligent systems, including machine learning, robotics, and related fields.
-
C.
Institute of Electronics and Telecommunications
The Institute of Electronics and Telecommunications is a specialized research and academic unit at Hanoi University of Science and Technology focusing on electronics, communications, and related technologies.
-
D.
Max Planck Institute for Informatics
The Max Planck Institute for Informatics is a leading German research institute specializing in computer science, particularly algorithms, data science, and artificial intelligence.
-
E.
Institute of Electronics, Communications and Information Technology
The Institute of Electronics, Communications and Information Technology is a research and innovation center at Queen’s University Belfast focused on advanced electronics, telecommunications, and information technologies.
- 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_69a88a174ab48190a5db20c132e5dccf |
completed | March 4, 2026, 7:37 p.m. |
| NER | Named-entity recognition | batch_69abbe0543108190862dd9a4a861c758 |
completed | March 7, 2026, 5:56 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae51b63e4081908a5d87af5d17d3c4 |
completed | March 9, 2026, 4:51 a.m. |
| NEDg | Description generation | batch_69ae52d29d708190809ee4d5047b2755 |
completed | March 9, 2026, 4:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae532ec8808190b1ecd8c4f66df30d |
completed | March 9, 2026, 4:57 a.m. |
Created at: March 4, 2026, 7:44 p.m.