Triple
T37107841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Les moulins de mon cœur |
E918898
|
entity |
| Predicate | isFrenchVersionOf |
P91232
|
FINISHED |
| Object | The Windmills of Your Mind |
—
|
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: The Windmills of Your Mind | Statement: [Les moulins de mon cœur, isFrenchVersionOf, The Windmills of Your Mind]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isFrenchVersionOf Context triple: [Les moulins de mon cœur, isFrenchVersionOf, The Windmills of Your Mind]
-
A.
isFrancophoneCounterpartOf
chosen
Indicates that one entity serves as the French-speaking or French-language equivalent or counterpart of another entity.
-
B.
handlesFrenchReleaseOf
Indicates that one entity is responsible for managing or overseeing the French release of another entity.
-
C.
containsFrenchPhrases
Indicates that the subject includes one or more phrases expressed in the French language.
-
D.
correspondsToAbbreviationInFrench
Indicates that one entity is the full form or expression for which the other entity serves as the abbreviation in French.
-
E.
isFrenchLanguageInstitution
Indicates that an institution primarily uses, promotes, or is officially associated with the French language.
- F. None of above.
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_69f76e9b99c8819096164b21ff5bd996 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fb344c60f8819090f2e21e1e61d621 |
completed | May 6, 2026, 12:30 p.m. |
| PD | Predicate disambiguation | batch_69fb2f642db08190b562725502c74ea6 |
completed | May 6, 2026, 12:09 p.m. |
Created at: May 3, 2026, 4:14 p.m.