Triple
T24810962
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jones calculus |
E620785
|
entity |
| Predicate | cannotDirectlyDescribe |
P93422
|
FINISHED |
| Object | partially polarized light |
—
|
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: partially polarized light | Statement: [Jones calculus, cannotDirectlyDescribe, partially polarized light]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cannotDirectlyDescribe Context triple: [Jones calculus, cannotDirectlyDescribe, partially polarized light]
-
A.
cannotExpress
Indicates that one entity is unable to convey, articulate, or communicate something (such as a feeling, idea, or message) to another entity.
-
B.
notDescribedAs
Indicates that an entity is explicitly not characterized, labeled, or referred to using a particular description or term.
-
C.
cannotRepresent
Indicates that one entity is not able or not permitted to act as a representative or stand-in for another entity in a given context.
-
D.
areUnderdescribed
Indicates that the entities lack sufficient detail or explanation relative to what is needed or expected.
-
E.
notConstructibleDirectly
chosen
Indicates that the entity cannot be instantiated or created directly, typically requiring an alternative or indirect construction method.
- 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_69e2fabf26bc8190b191faac8f67065b |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f42d9000b8819081ea2605f3c193d6 |
completed | May 1, 2026, 4:35 a.m. |
| PD | Predicate disambiguation | batch_69f420f471a0819095a6cd24ed8f7476 |
completed | May 1, 2026, 3:41 a.m. |
Created at: April 18, 2026, 4:50 a.m.