Triple
T22528396
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Youssef Chahine |
E556965
|
entity |
| Predicate | spouseOf |
P13
|
FINISHED |
| Object | Colette Chahine |
—
|
NE NERFINISHED |
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: Colette Chahine | Statement: [Youssef Chahine, spouseOf, Colette Chahine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Colette Chahine Context triple: [Youssef Chahine, spouseOf, Colette Chahine]
-
A.
Colette Chahine
chosen
Colette Chahine was the wife of renowned Egyptian film director Youssef Chahine.
-
B.
Nadine Chahine
Nadine Chahine is a renowned Lebanese type designer known for her work on Arabic and Latin typefaces and her leadership roles in major global type foundries.
-
C.
Andrée Chedid
Andrée Chedid was a Franco-Egyptian poet and novelist known for her lyrical explorations of exile, identity, and the human condition.
-
D.
Hédi Chaker
Hédi Chaker was a prominent Tunisian nationalist leader and independence activist who played a key role in the country’s anti-colonial movement.
-
E.
Michèle Ray-Gavras
Michèle Ray-Gavras is a French journalist, filmmaker, and producer known for her documentary work and for collaborating on politically engaged cinema.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e11e57483c8190b0887c4f8ff26446 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15ed4d4608190ba93bb54f15334a5 |
completed | April 29, 2026, 1:28 a.m. |
Created at: April 16, 2026, 8:51 p.m.