Triple
T20997406
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 8½ Women |
E517184
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Natacha Amal
Natacha Amal is a Belgian actress known for her work in European film and television, particularly in French-language productions.
|
E1462093
|
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: Natacha Amal | Statement: [8½ Women, starring, Natacha Amal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Natacha Amal Context triple: [8½ Women, starring, Natacha Amal]
-
A.
Nahla Ariela Aubry
Nahla Ariela Aubry is the daughter of American actress Halle Berry and Canadian model Gabriel Aubry.
-
B.
Natacha Karam
Natacha Karam is a British-Lebanese actress best known for her prominent television roles, including a main role on the procedural drama series "9-1-1: Lone Star."
-
C.
Lila Yacoub
Lila Yacoub is a film producer known for her work on independent features such as Noah Baumbach’s comedy-drama "Mistress America."
-
D.
Alexis Mdivani
Alexis Mdivani was a Georgian-born aristocrat and member of the socially prominent "Marrying Mdivanis," known for his high-profile marriage into great wealth and status.
-
E.
Amal Alamuddin
Amal Alamuddin, better known as Amal Clooney, is a prominent Lebanese-British barrister and human rights lawyer recognized for her high-profile international law cases and advocacy work.
- 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: Natacha Amal Triple: [8½ Women, starring, Natacha Amal]
Generated description
Natacha Amal is a Belgian actress known for her work in European film and television, particularly in French-language productions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Natacha Amal Target entity description: Natacha Amal is a Belgian actress known for her work in European film and television, particularly in French-language productions.
-
A.
Nahla Ariela Aubry
Nahla Ariela Aubry is the daughter of American actress Halle Berry and Canadian model Gabriel Aubry.
-
B.
Natacha Karam
Natacha Karam is a British-Lebanese actress best known for her prominent television roles, including a main role on the procedural drama series "9-1-1: Lone Star."
-
C.
Lila Yacoub
Lila Yacoub is a film producer known for her work on independent features such as Noah Baumbach’s comedy-drama "Mistress America."
-
D.
Alexis Mdivani
Alexis Mdivani was a Georgian-born aristocrat and member of the socially prominent "Marrying Mdivanis," known for his high-profile marriage into great wealth and status.
-
E.
Amal Alamuddin
Amal Alamuddin, better known as Amal Clooney, is a prominent Lebanese-British barrister and human rights lawyer recognized for her high-profile international law cases and advocacy work.
- 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_69e0b5006e2881909fc2383f841740cc |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6fc21838081909872eed21bc12a08 |
completed | April 21, 2026, 4:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a093b4fd8748190b90a50feac5c7517 |
completed | May 17, 2026, 3:51 a.m. |
| NEDg | Description generation | batch_6a093f361a288190bc373e95f7e9dd63 |
completed | May 17, 2026, 4:08 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a093fa8a998819080a96e67d34a5f52 |
completed | May 17, 2026, 4:10 a.m. |
Created at: April 16, 2026, 1:51 p.m.