Triple
T8994191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Costa-Gavras |
E214860
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
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.
|
E772838
|
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: Michèle Ray-Gavras | Statement: [Costa-Gavras, spouse, Michèle Ray-Gavras]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michèle Ray-Gavras Context triple: [Costa-Gavras, spouse, Michèle Ray-Gavras]
-
A.
Agnès Godard
Agnès Godard is a renowned French cinematographer celebrated for her long-standing collaboration with director Claire Denis and her distinctive, atmospheric visual style.
-
B.
Monique Dunan
Monique Dunan was a costume designer known for her work on the film "Fedora."
-
C.
Brigitte Aron
Brigitte Aron is known primarily as the daughter of the influential French philosopher, sociologist, and political commentator Raymond Aron.
-
D.
Violette Nozière
Violette Nozière is a 1978 French crime drama film by Claude Chabrol that recounts the true story of a notorious 1930s French parricide case.
-
E.
Mireille Mossé
Mireille Mossé is an actress known for her role in the visually distinctive French fantasy film "The City of Lost Children."
- 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: Michèle Ray-Gavras Triple: [Costa-Gavras, spouse, Michèle Ray-Gavras]
Generated description
Michèle Ray-Gavras is a French journalist, filmmaker, and producer known for her documentary work and for collaborating on politically engaged cinema.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michèle Ray-Gavras Target entity description: Michèle Ray-Gavras is a French journalist, filmmaker, and producer known for her documentary work and for collaborating on politically engaged cinema.
-
A.
Agnès Godard
Agnès Godard is a renowned French cinematographer celebrated for her long-standing collaboration with director Claire Denis and her distinctive, atmospheric visual style.
-
B.
Monique Dunan
Monique Dunan was a costume designer known for her work on the film "Fedora."
-
C.
Brigitte Aron
Brigitte Aron is known primarily as the daughter of the influential French philosopher, sociologist, and political commentator Raymond Aron.
-
D.
Violette Nozière
Violette Nozière is a 1978 French crime drama film by Claude Chabrol that recounts the true story of a notorious 1930s French parricide case.
-
E.
Mireille Mossé
Mireille Mossé is an actress known for her role in the visually distinctive French fantasy film "The City of Lost Children."
- 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_69ca83a05c608190bdfdbdb25e994b39 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc687798a881908e6fdd9a39219f1d |
completed | April 1, 2026, 12:36 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdb9531748190bd710e0b386b2cbe |
completed | April 3, 2026, 3:24 p.m. |
| NEDg | Description generation | batch_69cfdc48f22081909f17ec4c5542da47 |
completed | April 3, 2026, 3:27 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69cfdcecebe48190a2ede4c8400b3b42 |
completed | April 3, 2026, 3:29 p.m. |
Created at: March 30, 2026, 7:04 p.m.