Triple
T17128948
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ramon Casas |
E415672
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Madeleine |
E215457
|
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: Madeleine | Statement: [Ramon Casas, notableWork, Madeleine]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Madeleine Context triple: [Ramon Casas, notableWork, Madeleine]
-
A.
Madeleine
chosen
Madeleine is a feminine given name, commonly used in French and English, derived from Magdalene and often associated with literary and cultural figures.
-
B.
Madeleine
Madeleine is a Paris Métro station in central Paris that serves as an interchange between several metro lines, including the automated Line 14.
-
C.
Madeleine
"Madeleine" is a 1950 British crime drama film directed by David Lean and starring Ann Todd, based on the true story of a 19th-century Glasgow woman accused of poisoning her lover.
-
D.
Louisette
Louisette is the given name of Louisette Bertholle, a French chef and co-author of the influential cookbook "Mastering the Art of French Cooking."
-
E.
Madelaine
Madelaine is a character in the Danish crime thriller film "The Salvation."
- 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_69d886d15af4819092f92f8a129763e6 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f0291ee881908fb10a8ccd7faa41 |
completed | April 18, 2026, 8:57 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01482af1288190b7fdc8a84d0edeaf |
completed | May 11, 2026, 3:08 a.m. |
Created at: April 10, 2026, 5:36 a.m.