Triple
T7570488
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rayleigh scattering |
E179225
|
entity |
| Predicate | moreEffectiveAt |
P73273
|
FINISHED |
| Object | shorter wavelengths |
—
|
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: shorter wavelengths | Statement: [Rayleigh scattering, moreEffectiveAt, shorter wavelengths]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: moreEffectiveAt Context triple: [Rayleigh scattering, moreEffectiveAt, shorter wavelengths]
-
A.
strongerAt
chosen
Indicates that one entity has greater strength, power, or effectiveness than another in a specified context, condition, or domain.
-
B.
effectiveFor
Indicates that one entity successfully produces the intended effect, benefit, or desired outcome for another entity or condition.
-
C.
wirksamAb
Indicates the point in time from which something (such as a rule, contract, or condition) becomes effective or valid.
-
D.
usedAgainst
Indicates that one entity is employed, applied, or deployed in opposition to, or for the purpose of affecting, another entity.
-
E.
competitiveEffect
Indicates that one entity’s actions or presence influence another entity’s ability to compete, typically by enhancing or diminishing its competitive position or performance.
- 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_69c69f316e50819081a271c85c06f918 |
completed | March 27, 2026, 3:16 p.m. |
| NER | Named-entity recognition | batch_69c6f920540c8190817712db5aa3eeff |
completed | March 27, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69c6f4de77048190b8769e717fdcf8e7 |
completed | March 27, 2026, 9:21 p.m. |
Created at: March 27, 2026, 3:51 p.m.