Triple
T19894751
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michel Verne |
E478121
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Michel Verne |
—
|
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: Michel Verne | Statement: [Michel Verne, name, Michel Verne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michel Verne Context triple: [Michel Verne, name, Michel Verne]
-
A.
Michel Verne
chosen
Michel Verne was a French writer and playwright best known as the son of novelist Jules Verne and for editing, completing, and sometimes controversially revising his father's later works.
-
B.
Pierre Verne
Pierre Verne was a 19th-century French lawyer and the father of famed science fiction author Jules Verne.
-
C.
Michel Drach
Michel Drach was a French film director and screenwriter known for his intimate, socially engaged dramas in postwar French cinema.
-
D.
Alain Glavieux
Alain Glavieux was a French engineer and information theorist best known as a co-inventor of turbo codes, a breakthrough in error-correcting coding that revolutionized digital communications.
-
E.
Pierre Boulle
Pierre Boulle was a French novelist best known for writing the science fiction novel that inspired the film "Planet of the Apes" and the war novel "The Bridge on the River Kwai."
- 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_69d8e51f32b08190b3687f4f60353250 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e659105d7481909131d9907ac0094b |
completed | April 20, 2026, 4:49 p.m. |
Created at: April 10, 2026, 1:52 p.m.