Triple
T1347274
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ETH Board |
E28799
|
entity |
| Predicate | oversees |
P46
|
FINISHED |
| Object |
Empa
Empa is a Swiss federal research institute focused on materials science and technology, known for developing innovative solutions for industry and society.
|
E154315
|
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: Empa | Statement: [ETH Board, oversees, Empa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Empa Context triple: [ETH Board, oversees, Empa]
-
A.
Warburg
Warburg is a prominent German-Jewish banking and philanthropic family historically influential in international finance and economic policy.
-
B.
Löhr
Löhr is a German-language surname borne by various notable individuals, including figures in military, arts, and public life.
-
C.
Sorbs
The Sorbs are a Slavic ethnic minority primarily living in eastern Germany, known for preserving their distinct Sorbian language and cultural traditions.
-
D.
Houffalize
Houffalize is a small town in the Belgian Ardennes known for its World War II history, outdoor tourism, and scenic natural surroundings.
-
E.
Hesse
Hesse is a federal state in central Germany known for its financial hub Frankfurt am Main and its mix of urban centers, forests, and historic towns.
- 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: Empa Triple: [ETH Board, oversees, Empa]
Generated description
Empa is a Swiss federal research institute focused on materials science and technology, known for developing innovative solutions for industry and society.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Empa Target entity description: Empa is a Swiss federal research institute focused on materials science and technology, known for developing innovative solutions for industry and society.
-
A.
Warburg
Warburg is a prominent German-Jewish banking and philanthropic family historically influential in international finance and economic policy.
-
B.
Löhr
Löhr is a German-language surname borne by various notable individuals, including figures in military, arts, and public life.
-
C.
Sorbs
The Sorbs are a Slavic ethnic minority primarily living in eastern Germany, known for preserving their distinct Sorbian language and cultural traditions.
-
D.
Houffalize
Houffalize is a small town in the Belgian Ardennes known for its World War II history, outdoor tourism, and scenic natural surroundings.
-
E.
Hesse
Hesse is a federal state in central Germany known for its financial hub Frankfurt am Main and its mix of urban centers, forests, and historic towns.
- 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_69a498571d248190a0ac9eb02d97097f |
completed | March 1, 2026, 7:49 p.m. |
| NER | Named-entity recognition | batch_69a4c2406c488190b2c04d54d9c5e94c |
completed | March 1, 2026, 10:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acc639201c81908ed9c9ac37cd358f |
completed | March 8, 2026, 12:43 a.m. |
| NEDg | Description generation | batch_69acc71a3e808190aecbb57a64f39b6b |
completed | March 8, 2026, 12:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acc88e4ec08190945b366524b83088 |
completed | March 8, 2026, 12:53 a.m. |
Created at: March 1, 2026, 7:56 p.m.