Triple
T14567424
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Darius Khondji |
E341819
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Viviane Khondji |
E341819
|
NE FINISHED |
How this triple was built (2 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: Viviane Khondji | Statement: [Darius Khondji, spouse, Viviane Khondji]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Viviane Khondji Context triple: [Darius Khondji, spouse, Viviane Khondji]
-
A.
Viviane Khondji
chosen
Viviane Khondji is known as the spouse of acclaimed cinematographer Darius Khondji.
-
B.
Marie Khondji
Marie Khondji is the daughter of acclaimed cinematographer Darius Khondji.
-
C.
Aliyah Khondji
Aliyah Khondji is a member of the Khondji family, known primarily as the daughter of acclaimed cinematographer Darius Khondji.
-
D.
Karine Franclet
Karine Franclet is a French politician who serves as the mayor of Aubervilliers, a suburb of Paris.
-
E.
Lola Khondji
Lola Khondji is a French filmmaker and cinematographer known for her work on visually distinctive, often experimental short films and music videos.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d822dcc6248190bed689984bceb0e2 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb38d89fc819086709fd3607b835f |
completed | April 14, 2026, 9:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd94b4013881908fddb8b3cf8494de |
completed | May 8, 2026, 7:45 a.m. |
Created at: April 10, 2026, 1:23 a.m.