Triple
T28943548
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | GW150914 |
E730519
|
entity |
| Predicate | luminosityPeak |
P21598
|
FINISHED |
| Object | about 3.6×10^49 watts |
—
|
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: about 3.6×10^49 watts | Statement: [GW150914, luminosityPeak, about 3.6×10^49 watts]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: luminosityPeak Context triple: [GW150914, luminosityPeak, about 3.6×10^49 watts]
-
A.
typicalPeakAbsoluteMagnitude
Indicates the usual or characteristic value of an object's peak absolute magnitude, representing its typical intrinsic brightness at maximum luminosity.
-
B.
lightcurveAmplitude
Indicates the measured range of brightness variation of an object over time in its light curve.
-
C.
luminosity_W
chosen
Indicates the luminosity of an object measured in watts, representing the total power it emits as electromagnetic radiation.
-
D.
totalLuminosity
Indicates the overall emitted light or radiant power produced by an entity, typically by summing or integrating the luminosity from all its parts or components.
-
E.
observationalProminence
Indicates that one entity stands out or is especially noticeable relative to others when observed.
- 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_69f043ea0aa88190a25acbf46157995a |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65b85839c8190be57052eaef1d74f |
completed | May 2, 2026, 8:16 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 8:38 a.m.