Triple
T16602362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Persephassa |
E403360
|
entity |
| Predicate | movementOfSound |
P2926
|
FINISHED |
| Object | around the audience |
—
|
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: around the audience | Statement: [Persephassa, movementOfSound, around the audience]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: movementOfSound Context triple: [Persephassa, movementOfSound, around the audience]
-
A.
followsSoundOf
Indicates that one entity moves or directs its attention by tracking the source or direction of a sound produced by another entity.
-
B.
soundCategory
Indicates the classification relationship where a sound is assigned to a particular category or type of sound.
-
C.
movementAcross
Indicates movement of an entity from one side or area to another, traversing through or over an intervening space or boundary.
-
D.
movementIn
chosen
Indicates a relationship where an entity moves within, into, or inside a specified area, space, or container.
-
E.
soundMotif
Indicates a recurring or thematically significant sound pattern associated with an entity, event, or context.
- 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_69d883880d0c81908b5fcd454e767b60 |
completed | April 10, 2026, 4:58 a.m. |
| NER | Named-entity recognition | batch_69e35d770a048190be42180b03efba0b |
completed | April 18, 2026, 10:31 a.m. |
| PD | Predicate disambiguation | batch_69e296aabc508190b3836a91b49113ad |
completed | April 17, 2026, 8:23 p.m. |
Created at: April 10, 2026, 5:17 a.m.