Triple
T16426845
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ministry of the Interior of the GDR |
E398964
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object |
MdI
MdI was the common abbreviation for the Ministry of the Interior of the German Democratic Republic, the state body responsible for internal security, police, and administrative affairs.
|
E1212797
|
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: MdI | Statement: [Ministry of the Interior of the GDR, shortName, MdI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MdI Context triple: [Ministry of the Interior of the GDR, shortName, MdI]
-
A.
MD
MD is a postgraduate medical degree focused on advanced clinical training and specialization for physicians.
-
B.
MD
MD is the vehicle registration code used on license plates for the Austrian district of Mödling.
-
C.
MD
MD is the station code used to identify Maitland railway station in New South Wales, Australia.
-
D.
MD
MD is the official two-letter United States Postal Service abbreviation used to designate the state of Maryland.
-
E.
Ramatlabama
Ramatlabama is a village and key border post between Botswana and South Africa that serves as an important road and rail crossing point.
- 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: MdI Triple: [Ministry of the Interior of the GDR, shortName, MdI]
Generated description
MdI was the common abbreviation for the Ministry of the Interior of the German Democratic Republic, the state body responsible for internal security, police, and administrative affairs.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: MdI Target entity description: MdI was the common abbreviation for the Ministry of the Interior of the German Democratic Republic, the state body responsible for internal security, police, and administrative affairs.
-
A.
MD
MD is a postgraduate medical degree focused on advanced clinical training and specialization for physicians.
-
B.
MD
MD is the vehicle registration code used on license plates for the Austrian district of Mödling.
-
C.
MD
MD is the station code used to identify Maitland railway station in New South Wales, Australia.
-
D.
MD
MD is the official two-letter United States Postal Service abbreviation used to designate the state of Maryland.
-
E.
Ramatlabama
Ramatlabama is a village and key border post between Botswana and South Africa that serves as an important road and rail crossing point.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e328fb6cd881908fb6cd1c60f5ac3c |
completed | April 18, 2026, 6:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00458168888190bd0be495efa5c563 |
completed | May 10, 2026, 8:44 a.m. |
| NEDg | Description generation | batch_6a004621f0908190ad97a15fec619765 |
completed | May 10, 2026, 8:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0046a88e048190baa78506808171b8 |
completed | May 10, 2026, 8:49 a.m. |
Created at: April 10, 2026, 5:09 a.m.