Triple
T8894640
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | La femme qui pleure |
E211774
|
entity |
| Predicate | useOfStyle |
P64230
|
FINISHED |
| Object | fragmented forms |
—
|
LITERAL 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: fragmented forms | Statement: [La femme qui pleure, useOfStyle, fragmented forms]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: useOfStyle Context triple: [La femme qui pleure, useOfStyle, fragmented forms]
-
A.
usedStyle
chosen
Indicates that one entity employed or applied a particular style, method, or manner associated with another entity.
-
B.
usedWithStyle
Indicates that something is employed or applied in conjunction with a particular style or stylistic manner.
-
C.
usesAsStyleOf
Indicates that one entity adopts or applies another entity as a stylistic model, method, or manner of expression.
-
D.
styleNameUsage
Indicates how a particular style name is applied or used in relation to an entity or context.
-
E.
usesProductionStyle
Indicates that one entity creates, presents, or operates another entity using a particular production style or method.
- 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_69ca83918d3081909b326fa3750cb8c8 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc61be2c2081908f39cccdc149872d |
completed | April 1, 2026, 12:07 a.m. |
| PD | Predicate disambiguation | batch_69cc5c2aec04819093c932fe51c0f08d |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:54 p.m.