Triple
T31945607
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sur les lagunes (in G minor) |
E815642
|
entity |
| Predicate | textSourceCollection |
P32304
|
FINISHED |
| Object | La Comédie de la mort |
—
|
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: La Comédie de la mort | Statement: [Sur les lagunes (in G minor), textSourceCollection, La Comédie de la mort]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: textSourceCollection Context triple: [Sur les lagunes (in G minor), textSourceCollection, La Comédie de la mort]
-
A.
textSources
Indicates that one entity serves as a source or origin for the text content associated with another entity.
-
B.
typicalSourceText
Indicates that the related entity is a common or representative textual source from which information, examples, or data about another entity are typically drawn.
-
C.
documentSource
Indicates that one entity serves as the origin, provider, or provenance source for a given document.
-
D.
corpus
chosen
Indicates that an entity is a collection or body of texts, documents, or linguistic data used as a unified set for analysis or reference.
-
E.
archiveSource
Indicates that one entity serves as the originating source or provider of materials or data that are stored or preserved in an archive associated with another 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_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.