Triple
T23838378
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Improvisation I sur Mallarmé |
E590914
|
entity |
| Predicate | sharesTextSourceWith |
P153828
|
FINISHED |
| Object | Improvisation II sur Mallarmé |
—
|
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: Improvisation II sur Mallarmé | Statement: [Improvisation I sur Mallarmé, sharesTextSourceWith, Improvisation II sur Mallarmé]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesTextSourceWith Context triple: [Improvisation I sur Mallarmé, sharesTextSourceWith, Improvisation II sur Mallarmé]
-
A.
sharesUniverseWith
Indicates that two entities exist within the same fictional or narrative universe, implying shared continuity, setting, or canon.
-
B.
shareWith
Indicates that something is given, disclosed, or made accessible by one entity to another entity.
-
C.
sharesContentAs
Indicates that one entity makes its content available to or distributes its content through another entity or medium.
-
D.
sharesContextWith
Indicates that two entities occur within or are associated with the same situational, semantic, or environmental context.
-
E.
sharesWith
Indicates that one entity gives another entity access to or use of something it possesses.
- F. None of above. chosen
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_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c884c800819090d301740e1966cc |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f156036ad48190bc2ffdaf39218bcb |
completed | April 29, 2026, 12:51 a.m. |
| PDg | Predicate description generation | batch_69f158b0e320819090b947ee7eb14116 |
completed | April 29, 2026, 1:02 a.m. |
Created at: April 17, 2026, 8:08 p.m.