Triple
T6010701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AMS-02 experiment |
E133821
|
entity |
| Predicate | hasMeasured |
P43487
|
FINISHED |
| Object | positron fraction in cosmic rays |
—
|
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: positron fraction in cosmic rays | Statement: [AMS-02 experiment, hasMeasured, positron fraction in cosmic rays]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMeasured Context triple: [AMS-02 experiment, hasMeasured, positron fraction in cosmic rays]
-
A.
hasMeasurement
Indicates that an entity is associated with a specific measured value, often including a unit or measurement context.
-
B.
measured
chosen
Indicates that one entity has determined or quantified a property, amount, or extent of another entity using some standard or instrument.
-
C.
wasPreviouslyMeasuredAs
Indicates that an entity had a specific measurement or value at an earlier time, which may differ from its current measurement.
-
D.
measuredBy
Indicates that something’s quantity, extent, or value is determined or expressed using a particular measurement method, instrument, or unit.
-
E.
hasWellMeasuredDistances
Indicates that accurate and reliable distance measurements have been obtained between the related entities.
- 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_69c0087361a48190905c6b55969852b8 |
completed | March 22, 2026, 3:19 p.m. |
| NER | Named-entity recognition | batch_69c04f4ffa008190a8ef701b82260219 |
completed | March 22, 2026, 8:21 p.m. |
| PD | Predicate disambiguation | batch_69c049e4daf4819099bf870dc700e0a2 |
completed | March 22, 2026, 7:58 p.m. |
Created at: March 22, 2026, 4:06 p.m.