Triple
T16431064
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HMI |
E399070
|
entity |
| Predicate | spectralLineType |
P84901
|
FINISHED |
| Object | photospheric iron absorption line |
—
|
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: photospheric iron absorption line | Statement: [HMI, spectralLineType, photospheric iron absorption line]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: spectralLineType Context triple: [HMI, spectralLineType, photospheric iron absorption line]
-
A.
hasSpectralLines
chosen
Indicates that one entity exhibits or is characterized by specific spectral lines associated with another entity.
-
B.
lineType
Indicates the specific category or style of a line used in a representation, such as its function or visual convention.
-
C.
spectralLineColor
Indicates the color associated with a specific spectral line observed in an emission or absorption spectrum.
-
D.
spectralTypesPresent
Indicates that certain spectral types are present or occur within a given context or set of entities.
-
E.
spectralClass
Indicates the classification of an astronomical object based on the characteristics of its spectrum, such as temperature and spectral features.
- 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_69d87f2b9024819085c20e52de95d583 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32b9dffe48190a23852f828af55d8 |
completed | April 18, 2026, 6:58 a.m. |
| PD | Predicate disambiguation | batch_69e22701d2288190bf8676050758f172 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:10 a.m.