Triple
T23244122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cepheid variables |
E581535
|
entity |
| Predicate | hasLightCurveShape |
P132917
|
FINISHED |
| Object | sawtooth-like in many cases |
—
|
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: sawtooth-like in many cases | Statement: [Cepheid variables, hasLightCurveShape, sawtooth-like in many cases]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLightCurveShape Context triple: [Cepheid variables, hasLightCurveShape, sawtooth-like in many cases]
-
A.
hasLightcurveMeasurements
Indicates that an entity has associated lightcurve measurements, representing recorded variations in its brightness over time.
-
B.
lightCurveType
chosen
Indicates the classification of how an object's brightness changes over time as represented by its light curve.
-
C.
hasLightcurveVariations
Indicates that an object exhibits measurable changes in its brightness over time, as captured in its lightcurve.
-
D.
hasTransitLightCurve
Indicates that an object exhibits a measurable transit light curve, showing periodic dips in observed brightness due to another body passing in front of it.
-
E.
lightCurveBehavior
Indicates how the intensity or brightness of an object changes over time, typically as represented in its light curve.
- 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_69e24606b17c81908aba1a4911c8a8ba |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192efd44c8190b179b4d1cb71efa5 |
completed | April 29, 2026, 5:11 a.m. |
| PD | Predicate disambiguation | batch_69effcdadec0819092ec1749ee453b4e |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:10 p.m.