Triple
T29587181
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | L’Âme en fleur |
E754050
|
entity |
| Predicate | isBySameAuthorAs |
P98868
|
FINISHED |
| Object | Les Misérables |
—
|
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: Les Misérables | Statement: [L’Âme en fleur, isBySameAuthorAs, Les Misérables]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBySameAuthorAs Context triple: [L’Âme en fleur, isBySameAuthorAs, Les Misérables]
-
A.
workBySameAuthorAs
chosen
Indicates that two works share the same author, i.e., they were created by the same person or entity.
-
B.
authorSameAs
Indicates that two author identifiers or representations refer to the same underlying author.
-
C.
complementsWorkBySameAuthor
Indicates that one work enhances, completes, or supplements another work created by the same author.
-
D.
workInCollectionBySameAuthor
Indicates that one work is included in a collection whose other contents are by the same author as that work.
-
E.
collectionBySameAuthor
Indicates that multiple items in a collection are all created or authored by the same individual or entity.
- 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_69f0ef836ac88190bd809dc58b5ec907 |
completed | April 28, 2026, 5:33 p.m. |
| NER | Named-entity recognition | batch_69f66d7f46c481908cab81ff3be2b98b |
completed | May 2, 2026, 9:32 p.m. |
| PD | Predicate disambiguation | batch_69f6659d36208190b01412600a4ed57d |
completed | May 2, 2026, 8:59 p.m. |
Created at: April 28, 2026, 6:11 p.m.