Triple
T10852687
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DONUT experiment |
E256187
|
entity |
| Predicate | observedDecayProduct |
P5370
|
FINISHED |
| Object | tau lepton |
—
|
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: tau lepton | Statement: [DONUT experiment, observedDecayProduct, tau lepton]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: observedDecayProduct Context triple: [DONUT experiment, observedDecayProduct, tau lepton]
-
A.
betaDecayInvolves
Indicates that a beta decay process includes or is characterized by the participation of a specified particle, product, or sub-process.
-
B.
decayWidth
Indicates the total probability per unit time (or corresponding energy measure) that an unstable particle will decay via all possible channels.
-
C.
decayMode
chosen
Indicates the specific process or pathway by which an unstable entity transforms or decays into other products.
-
D.
primaryDecayChannelStudied
Indicates that the primary mode of decay for a particle or system is the main subject of investigation or analysis.
-
E.
typeOfIsotopesProduced
Indicates the kinds or categories of isotopes that are generated or produced by a given process, source, or entity.
- 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_69d6aa83d1448190a66d93c32394d21f |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d75134299481909459fd87917261a7 |
completed | April 9, 2026, 7:11 a.m. |
| PD | Predicate disambiguation | batch_69d70d2b51448190bae748ed6c23edde |
completed | April 9, 2026, 2:21 a.m. |
Created at: April 8, 2026, 9:20 p.m.