Triple
T16147738
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anamaria Marinca |
E391828
|
entity |
| Predicate | hasRole |
P161
|
FINISHED |
| Object |
Johan’s wife in Storm
Johan’s wife in *Storm* is a supporting character portrayed by Anamaria Marinca in the 2009 European political thriller film.
|
E1196985
|
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: Johan’s wife in Storm | Statement: [Anamaria Marinca, hasRole, Johan’s wife in Storm]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Johan’s wife in Storm Context triple: [Anamaria Marinca, hasRole, Johan’s wife in Storm]
-
A.
Johan
Johan is the given first name of the Swedish playwright and novelist August Strindberg.
-
B.
Johan
Johan is a masculine given name of Scandinavian origin, commonly used in countries such as Norway, Sweden, and Denmark.
-
C.
Johan
Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
-
D.
Stefan Holt
Stefan Holt is an American television news anchor and journalist, known for his work with NBC-owned stations in Chicago and New York and as the son of longtime NBC Nightly News anchor Lester Holt.
-
E.
Joha
"Joha" is a popular Afrobeats track by Nigerian singer Asake, known for its catchy rhythm and street-influenced sound.
- 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: Johan’s wife in Storm Triple: [Anamaria Marinca, hasRole, Johan’s wife in Storm]
Generated description
Johan’s wife in *Storm* is a supporting character portrayed by Anamaria Marinca in the 2009 European political thriller film.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Johan’s wife in Storm Target entity description: Johan’s wife in *Storm* is a supporting character portrayed by Anamaria Marinca in the 2009 European political thriller film.
-
A.
Johan
Johan is the given first name of the Swedish playwright and novelist August Strindberg.
-
B.
Johan
Johan is the given first name of J. Erik Jonsson, an American businessman and philanthropist who co-founded Texas Instruments and served as mayor of Dallas.
-
C.
Johan
Johan is a masculine given name of Scandinavian origin, commonly used in countries such as Norway, Sweden, and Denmark.
-
D.
Stefan Holt
Stefan Holt is an American television news anchor and journalist, known for his work with NBC-owned stations in Chicago and New York and as the son of longtime NBC Nightly News anchor Lester Holt.
-
E.
Joha
"Joha" is a popular Afrobeats track by Nigerian singer Asake, known for its catchy rhythm and street-influenced sound.
- 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_69d87f1c65e48190aa2b4c472e9bafc4 |
completed | April 10, 2026, 4:39 a.m. |
| NER | Named-entity recognition | batch_69e21d9551e081908391061b092ff31b |
completed | April 17, 2026, 11:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fff7a7dc3481909f933acd72d6feff |
completed | May 10, 2026, 3:12 a.m. |
| NEDg | Description generation | batch_69fff81bb0008190947eeff64dc8eb88 |
completed | May 10, 2026, 3:14 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fff8905ce48190b99f8cc3504efba2 |
completed | May 10, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:01 a.m.