Triple
T20129624
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Military District of Russia |
E490851
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object |
SMD
SMD is the abbreviation for Russia’s Southern Military District, a major regional command responsible for military operations in the country’s south and parts of the Caucasus.
|
E1412515
|
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: SMD | Statement: [Southern Military District of Russia, hasAbbreviation, SMD]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: SMD Context triple: [Southern Military District of Russia, hasAbbreviation, SMD]
-
A.
SMD
SMD is the IATA airport code for Smith Field, a public airport serving Fort Wayne, Indiana, in the United States.
-
B.
SMD
SMD is the abbreviated name for the Italian Defence General Staff, the top military command responsible for coordinating Italy’s armed forces.
-
C.
SKMD
SKMD is the ICAO airport code assigned to Olaya Herrera Airport in Medellín, Colombia.
-
D.
SMT
SMT is the abbreviation used for Parnall Correctional Facility, a state prison located in Jackson, Michigan.
-
E.
SMT
SMT is a field in computer science and mathematical logic that studies the satisfiability of logical formulas with respect to background theories such as arithmetic, arrays, and bit-vectors.
- 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: SMD Triple: [Southern Military District of Russia, hasAbbreviation, SMD]
Generated description
SMD is the abbreviation for Russia’s Southern Military District, a major regional command responsible for military operations in the country’s south and parts of the Caucasus.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: SMD Target entity description: SMD is the abbreviation for Russia’s Southern Military District, a major regional command responsible for military operations in the country’s south and parts of the Caucasus.
-
A.
SMD
SMD is the IATA airport code for Smith Field, a public airport serving Fort Wayne, Indiana, in the United States.
-
B.
SMD
SMD is the abbreviated name for the Italian Defence General Staff, the top military command responsible for coordinating Italy’s armed forces.
-
C.
SKMD
SKMD is the ICAO airport code assigned to Olaya Herrera Airport in Medellín, Colombia.
-
D.
SMT
SMT is the abbreviation used for Parnall Correctional Facility, a state prison located in Jackson, Michigan.
-
E.
SMT
SMT is a field in computer science and mathematical logic that studies the satisfiability of logical formulas with respect to background theories such as arithmetic, arrays, and bit-vectors.
- 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_69da62651a0c8190a3e05e95e056a66b |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e66760b8f08190a66fbb2e9e3925a3 |
completed | April 20, 2026, 5:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a082ddbae5481908ee89666afa6296e |
completed | May 16, 2026, 8:42 a.m. |
| NEDg | Description generation | batch_6a082ed267588190ac209a5f5fcdac16 |
completed | May 16, 2026, 8:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a082f5360ac8190bdfe653cb48c6ecb |
completed | May 16, 2026, 8:48 a.m. |
Created at: April 11, 2026, 11:31 p.m.