Triple
T23340913
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les Huguenots |
E591731
|
entity |
| Predicate | librettist |
P1141
|
FINISHED |
| Object | Eugène Scribe |
—
|
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: Eugène Scribe | Statement: [Les Huguenots, librettist, Eugène Scribe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eugène Scribe Context triple: [Les Huguenots, librettist, Eugène Scribe]
-
A.
Eugène Scribe
chosen
Eugène Scribe was a prolific 19th-century French dramatist and librettist, renowned for his well-crafted comedies and influential opera libretti that shaped European theater and music.
-
B.
Ernest-Aimé Feydeau
Ernest-Aimé Feydeau was a 19th-century French novelist and writer known for his realist works and as the father of playwright Georges Feydeau.
-
C.
Eugène Labiche
Eugène Labiche was a 19th-century French playwright best known for his witty, fast-paced vaudevilles and comedies of manners that satirized the bourgeoisie.
-
D.
Claude Guerney
Claude Guerney was a screenwriter best known for his work on the classic British mystery film "Green for Danger."
-
E.
Ernest Mercier
Ernest Mercier was a French industrialist and engineer best known for founding the major energy company that later became Total S.A.
- 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_69e25d20e3d08190bcede87673cafb25 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f198329d9c8190992627afa9b54bed |
completed | April 29, 2026, 5:33 a.m. |
Created at: April 17, 2026, 5:18 p.m.