Triple
T23269448
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | DAMA/LIBRA |
E588247
|
entity |
| Predicate | usesReadout |
P149343
|
FINISHED |
| Object | photomultiplier tubes |
—
|
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: photomultiplier tubes | Statement: [DAMA/LIBRA, usesReadout, photomultiplier tubes]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesReadout Context triple: [DAMA/LIBRA, usesReadout, photomultiplier tubes]
-
A.
readout
Indicates that one entity reports, displays, or outputs the measured or computed value of another entity.
-
B.
hasReadoutTime
Indicates the duration or timing characteristics required to read out or retrieve data from a device, sensor, or system.
-
C.
hasSignalReadout
chosen
Indicates that an entity provides or is associated with a measurable signal output that can be read or recorded.
-
D.
containsReading
Indicates that one entity includes or encompasses a particular reading (such as a measurement, value, or interpretation) within it.
-
E.
canRead
Indicates that one entity has the ability or permission to read or access the content of another 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_69e25d148adc819088efbf42672604e9 |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1957219188190b30bceffad1542da |
completed | April 29, 2026, 5:21 a.m. |
| PD | Predicate disambiguation | batch_69effcecabd88190856fb6e1d993e4dd |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:45 p.m.