Triple
T25261742
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Capitaine Alexandre |
E633320
|
entity |
| Predicate | notableWorkUnderName |
P4
|
FINISHED |
| Object | Feuillets d’Hypnos |
E633322
|
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: Feuillets d’Hypnos | Statement: [Capitaine Alexandre, notableWorkUnderName, Feuillets d’Hypnos]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableWorkUnderName Context triple: [Capitaine Alexandre, notableWorkUnderName, Feuillets d’Hypnos]
-
A.
notableWorkAs
Indicates a relationship where a particular work is recognized as a significant or distinguished creation associated with an entity.
-
B.
notableWorkWith
Indicates a relationship where two or more entities are recognized for having collaborated on or been jointly associated with a significant work or project.
-
C.
notableWorkIn
Indicates that an entity is known for or associated with a significant work, contribution, or achievement in a particular field or context.
-
D.
notableWork
chosen
Indicates that one entity is a significant or well-known work (such as a book, artwork, or creation) produced by another entity.
-
E.
notableWorkPublishedIn
Indicates that a notable work associated with an entity was published in a particular venue, medium, or publication.
- F. None of above.
Provenance (4 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_69e75a922ad481908f4f1f884583cb42 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f7be53890081909b1d93f30a8f31c6 |
completed | May 3, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1067f49358819093d0dba4fc80b2da |
completed | May 22, 2026, 2:28 p.m. |
| PD | Predicate disambiguation | batch_69f7bccacbac8190978976324c67db28 |
completed | May 3, 2026, 9:23 p.m. |
Created at: April 21, 2026, 1:13 p.m.