Triple
T23297101
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pleiades reflection nebulae |
E590202
|
entity |
| Predicate | scatteringType |
P21257
|
FINISHED |
| Object | preferential scattering of blue 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: preferential scattering of blue light | Statement: [Pleiades reflection nebulae, scatteringType, preferential scattering of blue light]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scatteringType Context triple: [Pleiades reflection nebulae, scatteringType, preferential scattering of blue light]
-
A.
dispersionType
chosen
Indicates the manner or pattern in which something is spread, scattered, or distributed relative to something else.
-
B.
scanType
Indicates the specific kind or category of scanning operation performed or required in a given context.
-
C.
dispersionMechanism
Indicates the process or method by which something (such as particles, organisms, or substances) is spread or distributed from one place to others.
-
D.
surfaceType
Indicates the kind or classification of surface associated with an entity or interaction.
-
E.
typeOfHit
Indicates the specific category or kind of hit or strike that occurred in an interaction or event.
- 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_69e25d1af9d88190a0b9b5e8fa608618 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f196cfc79081909966638cec48cf60 |
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.