Triple
T8474013
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gratian |
E200345
|
entity |
| Predicate | mother |
P120
|
FINISHED |
| Object |
Marina Severa
Marina Severa was a Roman empress of the 4th century, known as the first wife of Emperor Valentinian I and the mother of Emperor Gratian.
|
E736715
|
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: Marina Severa | Statement: [Gratian, mother, Marina Severa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marina Severa Context triple: [Gratian, mother, Marina Severa]
-
A.
Marina
Marina is a recurring comedic character in the long-running British sitcom "Last of the Summer Wine," known for her flirtatious relationship with the married Howard.
-
B.
Marina
Marina is the given name of Marina von Neumann Whitman, an American economist and former General Motors executive.
-
C.
Marina
Marina is a female given name of Latin origin, commonly used in various cultures and often associated with the sea.
-
D.
Marina Rubicón
Marina Rubicón is a modern marina and leisure complex in Playa Blanca on the island of Lanzarote, featuring yacht moorings, shops, restaurants, and waterfront promenades.
-
E.
Marina Lu
Marina Lu is the mother of renowned cellist Yo-Yo Ma.
- 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: Marina Severa Triple: [Gratian, mother, Marina Severa]
Generated description
Marina Severa was a Roman empress of the 4th century, known as the first wife of Emperor Valentinian I and the mother of Emperor Gratian.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marina Severa Target entity description: Marina Severa was a Roman empress of the 4th century, known as the first wife of Emperor Valentinian I and the mother of Emperor Gratian.
-
A.
Marina
Marina is a recurring comedic character in the long-running British sitcom "Last of the Summer Wine," known for her flirtatious relationship with the married Howard.
-
B.
Marina
Marina is the given name of Marina von Neumann Whitman, an American economist and former General Motors executive.
-
C.
Marina
Marina is a female given name of Latin origin, commonly used in various cultures and often associated with the sea.
-
D.
Marina Rubicón
Marina Rubicón is a modern marina and leisure complex in Playa Blanca on the island of Lanzarote, featuring yacht moorings, shops, restaurants, and waterfront promenades.
-
E.
Marina Lu
Marina Lu is the mother of renowned cellist Yo-Yo Ma.
- 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_69ca831a4f348190bfdd09250e86ae35 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe4f7328481909ad19bcf8d182022 |
completed | March 31, 2026, 3:15 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce3a057b6c8190ad592110ca393ee2 |
completed | April 2, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_69ce3b1e188c8190ad894478141f6501 |
completed | April 2, 2026, 9:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce3c000e608190adf1b6499d382529 |
completed | April 2, 2026, 9:50 a.m. |
Created at: March 30, 2026, 6:11 p.m.