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.