Triple
T15178357
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Charles-Marie-Georges Huysmans |
E362671
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | En ménage |
E946092
|
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: En ménage | Statement: [Charles-Marie-Georges Huysmans, notableWork, En ménage]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: En ménage Context triple: [Charles-Marie-Georges Huysmans, notableWork, En ménage]
-
A.
En ménage
chosen
En ménage is an 1881 naturalist novel by French writer Joris-Karl Huysmans that portrays the disillusionment and domestic struggles of a Parisian couple.
-
B.
Les Deux Foyers
Les Deux Foyers is a lesser-known literary work by 19th-century French writer and dramatist Paul Meurice.
-
C.
Mon homme
Mon homme is a French film known in English as "My Man."
-
D.
La Paix du ménage
La Paix du ménage is a short story by Honoré de Balzac that portrays Parisian high society and domestic intrigue, later collected as part of his larger work La Comédie humaine.
-
E.
Trois femmes
Trois femmes is a French film whose story centers on the intertwined lives and emotional struggles of three women.
- 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_69d85a09a39c81908759f23268e2d408 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00663b4148190b647592eda315d1d |
completed | April 15, 2026, 9:42 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fec89061548190b0b10da00b8d937e |
completed | May 9, 2026, 5:39 a.m. |
Created at: April 10, 2026, 3:09 a.m.