Triple
T31945436
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Le spectre de la rose |
E815637
|
entity |
| Predicate | poetOfSourceText |
P36356
|
FINISHED |
| Object | Théophile Gautier |
—
|
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: Théophile Gautier | Statement: [Le spectre de la rose, poetOfSourceText, Théophile Gautier]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: poetOfSourceText Context triple: [Le spectre de la rose, poetOfSourceText, Théophile Gautier]
-
A.
lyricistOfSourcePoem
Indicates that one entity is the writer of the original poem on which another work (such as a song or adaptation) is based.
-
B.
poemAuthor
chosen
Indicates that one entity is the author or creator of a poem represented by the other entity.
-
C.
poet
Indicates that an entity creates poetry or is recognized for engaging in the activity of writing poems.
-
D.
poetAssociated
Indicates a relationship where a poet is connected or linked to another entity, such as a work, place, movement, or person, through relevance, collaboration, influence, or affiliation.
-
E.
favoritePoet
Indicates that one entity is the poet whom another entity prefers above all other poets.
- 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_69f348f42d188190a33fc8d20ec50517 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f6b27930d881909d5bef056bf5e7e5 |
completed | May 3, 2026, 2:27 a.m. |
| PD | Predicate disambiguation | batch_69f6b14faf608190a25b977c0740729c |
completed | May 3, 2026, 2:22 a.m. |
Created at: May 1, 2026, 12:06 a.m.