Triple
T25859562
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SPT-3G survey |
E651443
|
entity |
| Predicate | scienceCategory |
P135493
|
FINISHED |
| Object | secondary CMB anisotropies |
—
|
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: secondary CMB anisotropies | Statement: [SPT-3G survey, scienceCategory, secondary CMB anisotropies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scienceCategory Context triple: [SPT-3G survey, scienceCategory, secondary CMB anisotropies]
-
A.
scienceDomain
Indicates that one entity is a field, branch, or domain within science to which the other entity is related or belongs.
-
B.
hasScience
Indicates that an entity possesses, includes, or is associated with a particular scientific discipline, content, or attribute.
-
C.
scienceReturn
Indicates that an action or process yields scientific data, findings, or value as its outcome.
-
D.
secondScience
Indicates that the subject is the second entity in a sequence or ranking specifically within a scientific context or domain.
-
E.
subjectCategories
chosen
Indicates that an entity is associated with one or more subject-based categories or classifications.
- 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_69e7ab3a199c81909227cb964cacfe24 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f638d11c988190af7fd4572b08e038 |
completed | May 2, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69f63706b6008190993577193c85ff50 |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 22, 2026, 8:05 a.m.