Triple
T23298688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Freygish |
E590241
|
entity |
| Predicate | hasExpressiveQuality |
P70301
|
FINISHED |
| Object | cantorial sound |
—
|
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: cantorial sound | Statement: [Freygish, hasExpressiveQuality, cantorial sound]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasExpressiveQuality Context triple: [Freygish, hasExpressiveQuality, cantorial sound]
-
A.
hasExpressivity
Indicates that one entity possesses a certain level or type of expressive power, capability, or richness in representation relative to another.
-
B.
expressiveQuality
chosen
Indicates the distinctive emotional or stylistic character conveyed by something, such as how it feels, sounds, or appears in an expressive sense.
-
C.
hasExpressiveRole
Indicates that an entity serves a communicative or expressive function or role in relation to another entity or context.
-
D.
expressivePower
Indicates the degree to which one system, language, or formalism can represent or capture the behaviors, structures, or concepts expressible in another.
-
E.
expressivenessComparedTo
Indicates a comparison of how expressive one entity is relative to another in conveying meaning, emotion, or nuance.
- 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_69e25d1c0ecc8190a355aa229f06d0e0 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196d133448190bf350a9f51c1531c |
completed | April 29, 2026, 5:27 a.m. |
| PD | Predicate disambiguation | batch_69effcf325f88190b320268c3c551abb |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 5:03 p.m.