Triple
T974626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael |
E21023
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object |
Mihai
Mihai is a Romanian given name, equivalent to Michael, commonly used for males in Romania and other Romanian-speaking communities.
|
E114790
|
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: Mihai | Statement: [Michael, hasVariant, Mihai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mihai Context triple: [Michael, hasVariant, Mihai]
-
A.
Dumitru Erhan
Dumitru Erhan is a computer scientist and machine learning researcher known for influential work in deep learning and neural networks.
-
B.
Gheorghe Avramescu
Gheorghe Avramescu was a Romanian general during World War II who played a significant role on the Eastern Front and later in Romania’s switch to the Allied side.
-
C.
Daniel Ciobotea
Daniel Ciobotea is the current Patriarch of the Romanian Orthodox Church, serving as its supreme spiritual leader and highest-ranking bishop.
-
D.
Constantin Sănătescu
Constantin Sănătescu was a Romanian army general and statesman who led the country as prime minister after the fall of Ion Antonescu during World War II.
-
E.
Victor Vianu
Victor Vianu is a computer scientist known for his contributions to database theory and finite model theory, who has also served as editor-in-chief of leading theoretical computer science journals.
- 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: Mihai Triple: [Michael, hasVariant, Mihai]
Generated description
Mihai is a Romanian given name, equivalent to Michael, commonly used for males in Romania and other Romanian-speaking communities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mihai Target entity description: Mihai is a Romanian given name, equivalent to Michael, commonly used for males in Romania and other Romanian-speaking communities.
-
A.
Dumitru Erhan
Dumitru Erhan is a computer scientist and machine learning researcher known for influential work in deep learning and neural networks.
-
B.
Gheorghe Avramescu
Gheorghe Avramescu was a Romanian general during World War II who played a significant role on the Eastern Front and later in Romania’s switch to the Allied side.
-
C.
Daniel Ciobotea
Daniel Ciobotea is the current Patriarch of the Romanian Orthodox Church, serving as its supreme spiritual leader and highest-ranking bishop.
-
D.
Constantin Sănătescu
Constantin Sănătescu was a Romanian army general and statesman who led the country as prime minister after the fall of Ion Antonescu during World War II.
-
E.
Victor Vianu
Victor Vianu is a computer scientist known for his contributions to database theory and finite model theory, who has also served as editor-in-chief of leading theoretical computer science journals.
- 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_69a493c2b62c8190b616351789ec47f8 |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b460a5c0819087b03dfb8a3af2c2 |
completed | March 1, 2026, 9:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac170c0fdc8190b904ca5737764f5a |
completed | March 7, 2026, 12:16 p.m. |
| NEDg | Description generation | batch_69ac17c2e6f48190be6fce7f279957c4 |
completed | March 7, 2026, 12:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ac1844acec81909859605d2421a588 |
completed | March 7, 2026, 12:21 p.m. |
Created at: March 1, 2026, 7:40 p.m.