Triple
T22895186
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Academy of Economic Studies of Moldova |
E568153
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object |
ASEM
ASEM is a leading higher education institution in Moldova specializing in economics, business, and related social sciences.
|
E1560595
|
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: ASEM | Statement: [Academy of Economic Studies of Moldova, abbreviation, ASEM]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ASEM Context triple: [Academy of Economic Studies of Moldova, abbreviation, ASEM]
-
A.
ESSAIM
ESSAIM is a French military signals intelligence microsatellite constellation designed for electronic surveillance and space-based reconnaissance.
-
B.
ASE
ASE is the Amman Stock Exchange, the principal securities market of Jordan where stocks and other financial instruments are traded.
-
C.
ASE
ASE is a professional medical society dedicated to advancing cardiovascular ultrasound and improving patient care through education, research, and advocacy.
-
D.
ASE
ASE is the three-letter IATA airport code for Aspen–Pitkin County Airport, which serves the popular ski resort area of Aspen, Colorado.
-
E.
ASEMAN
ASEMAN is the radio callsign used by Iran Aseman Airlines, a regional and domestic carrier based in Iran.
- 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: ASEM Triple: [Academy of Economic Studies of Moldova, abbreviation, ASEM]
Generated description
ASEM is a leading higher education institution in Moldova specializing in economics, business, and related social sciences.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ASEM Target entity description: ASEM is a leading higher education institution in Moldova specializing in economics, business, and related social sciences.
-
A.
ESSAIM
ESSAIM is a French military signals intelligence microsatellite constellation designed for electronic surveillance and space-based reconnaissance.
-
B.
ASE
ASE is the Amman Stock Exchange, the principal securities market of Jordan where stocks and other financial instruments are traded.
-
C.
ASE
ASE is a professional medical society dedicated to advancing cardiovascular ultrasound and improving patient care through education, research, and advocacy.
-
D.
ASE
ASE is the three-letter IATA airport code for Aspen–Pitkin County Airport, which serves the popular ski resort area of Aspen, Colorado.
-
E.
ASEMAN
ASEMAN is the radio callsign used by Iran Aseman Airlines, a regional and domestic carrier based in Iran.
- 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_69e2458c23ec81908fa2570692c6614f |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f17fc83d688190a8ab5ea0aad1e7ec |
completed | April 29, 2026, 3:49 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bb9c59acc819090353ecaddac1624 |
completed | May 19, 2026, 1:15 a.m. |
| NEDg | Description generation | batch_6a0bbbf1fdb4819082a721c75958eaa1 |
completed | May 19, 2026, 1:25 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bbcaee9508190aa5c84a8930e15cd |
completed | May 19, 2026, 1:28 a.m. |
Created at: April 17, 2026, 3:40 p.m.