Triple
T21764365
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Impromptu |
E537238
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object |
Sofica Valor
Sofica Valor is a French film financing company that specializes in supporting the production of movies and audiovisual works through tax-incentivized investment funds.
|
E1501335
|
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: Sofica Valor | Statement: [Impromptu, productionCompany, Sofica Valor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sofica Valor Context triple: [Impromptu, productionCompany, Sofica Valor]
-
A.
Sofina
Sofina is a powerful Red Wizard and primary antagonist in the fantasy adventure film "Dungeons & Dragons: Honor Among Thieves."
-
B.
Sofi
Sofi is a feminine given name used in various cultures, often as a variant of "Sophie" or "Sophia."
-
C.
Sansia
Sansia is the former name of Sanxia District, a suburban area in New Taipei City, Taiwan, known for its historic old street and cultural heritage.
-
D.
Sifra
Sifra is a classical rabbinic midrash on the Book of Leviticus that systematically expounds its legal (halakhic) passages.
-
E.
Valeria
Valeria is a character in the Mexican film "Amores perros," a successful model whose life is dramatically altered by a devastating car accident.
- 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: Sofica Valor Triple: [Impromptu, productionCompany, Sofica Valor]
Generated description
Sofica Valor is a French film financing company that specializes in supporting the production of movies and audiovisual works through tax-incentivized investment funds.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sofica Valor Target entity description: Sofica Valor is a French film financing company that specializes in supporting the production of movies and audiovisual works through tax-incentivized investment funds.
-
A.
Sofina
Sofina is a powerful Red Wizard and primary antagonist in the fantasy adventure film "Dungeons & Dragons: Honor Among Thieves."
-
B.
Sofi
Sofi is a feminine given name used in various cultures, often as a variant of "Sophie" or "Sophia."
-
C.
Sansia
Sansia is the former name of Sanxia District, a suburban area in New Taipei City, Taiwan, known for its historic old street and cultural heritage.
-
D.
Sifra
Sifra is a classical rabbinic midrash on the Book of Leviticus that systematically expounds its legal (halakhic) passages.
-
E.
Valeria
Valeria is a character in the Mexican film "Amores perros," a successful model whose life is dramatically altered by a devastating car accident.
- 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_69e0c46f5d1c8190bf830409e98464e5 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f031a8a7f08190a4e50ebc24219585 |
completed | April 28, 2026, 4:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a3677fa80819082dbe7ba2fcb0421 |
completed | May 17, 2026, 9:43 p.m. |
| NEDg | Description generation | batch_6a0a373aca708190aae867f78c87b956 |
completed | May 17, 2026, 9:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a37e0bed48190b0319d62eaff5d1e |
completed | May 17, 2026, 9:49 p.m. |
Created at: April 16, 2026, 6:51 p.m.