Triple
T21066638
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Debye temperature |
E518989
|
entity |
| Predicate | isCutoffFor |
P9149
|
FINISHED |
| Object | phonon wave vectors in Debye model |
—
|
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: phonon wave vectors in Debye model | Statement: [Debye temperature, isCutoffFor, phonon wave vectors in Debye model]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCutoffFor Context triple: [Debye temperature, isCutoffFor, phonon wave vectors in Debye model]
-
A.
hasCutoffTime
Indicates that there is a specific time limit or deadline by which an action, event, or process must be completed or initiated.
-
B.
cutOff
Indicates that one entity causes another entity to be disconnected, interrupted, or severed from a source, flow, or continuation.
-
C.
isLimitOf
chosen
Indicates that one quantity, function, or sequence approaches a particular value as its input or index approaches some specified point or condition.
-
D.
cutOffDateYear
Indicates the calendar year that serves as the cutoff point beyond which something no longer applies, is valid, or is considered.
-
E.
isFinalHourOf
Indicates that one time period represents the last hour within the duration or schedule of another time-related entity.
- 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_69e0b505ef108190b25dd4033e2ff7eb |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e6feb455fc81909cc63fa0e87b6a35 |
completed | April 21, 2026, 4:36 a.m. |
| PD | Predicate disambiguation | batch_69e5dbf9d71881908cd85dfc37db93ca |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 2:45 p.m.