Triple
T29100147
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | π/4 DQPSK |
E736616
|
entity |
| Predicate | envelopeProperty |
P145284
|
FINISHED |
| Object | quasi-constant envelope |
—
|
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: quasi-constant envelope | Statement: [π/4 DQPSK, envelopeProperty, quasi-constant envelope]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: envelopeProperty Context triple: [π/4 DQPSK, envelopeProperty, quasi-constant envelope]
-
A.
enveloped
Indicates that one entity is completely or largely surrounded, covered, or enclosed by another.
-
B.
engagementEnvelope
Indicates the spatial or contextual bounds within which an interaction, operation, or engagement between entities is valid or permitted.
-
C.
envelopeShapes
chosen
Indicates a relationship where one entity defines or determines the geometric or boundary shape(s) that enclose or outline another entity.
-
D.
hasEnvoi
Indicates that one entity includes or is associated with an envoi, typically a concluding or dedicatory section appended to a main text or composition.
-
E.
extensionProperty
Indicates that one entity serves as an additional or extended attribute or property of another entity beyond its core or standard properties.
- 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_69f077ec765c81909474c88bcc8bab43 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69f66184e9208190a66378cac527bca9 |
completed | May 2, 2026, 8:41 p.m. |
| PD | Predicate disambiguation | batch_69f65c2376a08190be5215171e908e69 |
completed | May 2, 2026, 8:18 p.m. |
Created at: April 28, 2026, 11:11 a.m.