Triple
T8440795
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nina Sosanya |
E199345
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Marcella
Marcella is a British crime drama television series centered on a troubled former detective who returns to investigate a string of murders that echo an old case.
|
E733554
|
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: Marcella | Statement: [Nina Sosanya, notableWork, Marcella]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcella Context triple: [Nina Sosanya, notableWork, Marcella]
-
A.
Marcella Spruce
Marcella Spruce is the sister of American author Tabitha King and a member of the extended King literary family.
-
B.
Marica
Marica is a figure in Roman mythology, often associated with the Latin king Latinus as his mother and sometimes linked to a local water or nymph deity.
-
C.
Maeve
Maeve is a feminine given name of Irish origin, traditionally associated with a legendary queen of Connacht in Irish mythology.
-
D.
Marnie
Marnie is a 1964 psychological thriller film directed by Alfred Hitchcock, starring Tippi Hedren and Sean Connery, about a troubled woman with a mysterious past and compulsive thieving.
-
E.
Shula
Shula is a surname most famously associated with Don Shula, the legendary NFL coach of the Miami Dolphins.
- 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: Marcella Triple: [Nina Sosanya, notableWork, Marcella]
Generated description
Marcella is a British crime drama television series centered on a troubled former detective who returns to investigate a string of murders that echo an old case.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marcella Target entity description: Marcella is a British crime drama television series centered on a troubled former detective who returns to investigate a string of murders that echo an old case.
-
A.
Marcella Spruce
Marcella Spruce is the sister of American author Tabitha King and a member of the extended King literary family.
-
B.
Marica
Marica is a figure in Roman mythology, often associated with the Latin king Latinus as his mother and sometimes linked to a local water or nymph deity.
-
C.
Maeve
Maeve is a feminine given name of Irish origin, traditionally associated with a legendary queen of Connacht in Irish mythology.
-
D.
Marnie
Marnie is a 1964 psychological thriller film directed by Alfred Hitchcock, starring Tippi Hedren and Sean Connery, about a troubled woman with a mysterious past and compulsive thieving.
-
E.
Shula
Shula is a surname most famously associated with Don Shula, the legendary NFL coach of the Miami Dolphins.
- 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_69ca8314cd6c8190a6b8c2a1096e18f3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe138a94081908e306d22aaa39b24 |
completed | March 31, 2026, 2:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ce1d9140b48190ad0c493948a3de5e |
completed | April 2, 2026, 7:41 a.m. |
| NEDg | Description generation | batch_69ce1f12e1a081909d28b06c520353ef |
completed | April 2, 2026, 7:47 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ce1fb498448190a2737b8895f6bb48 |
completed | April 2, 2026, 7:50 a.m. |
Created at: March 30, 2026, 6:08 p.m.