Triple
T27134970
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | svedberg unit |
E681656
|
entity |
| Predicate | approximateValueInSeconds |
P4874
|
FINISHED |
| Object | 1e-13 s |
—
|
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: 1e-13 s | Statement: [svedberg unit, approximateValueInSeconds, 1e-13 s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateValueInSeconds Context triple: [svedberg unit, approximateValueInSeconds, 1e-13 s]
-
A.
exactValueInSeconds
Indicates that the related quantity or duration is specified as an exact number of seconds, with no approximation or alternative units.
-
B.
timePeriodApproximation
Indicates that the associated time period is an estimate or approximation rather than an exact, precise value.
-
C.
hasApproximateDuration
chosen
Indicates that one entity has a duration that is estimated or not exact, typically expressed as an approximate length of time.
-
D.
hasApproximateValue
Indicates that one entity’s value is close to, but not exactly equal to, the value of another entity within an acceptable margin of error.
-
E.
approximateTimeInYear
Indicates that one time-related entity represents an estimated or non-exact point or interval within a given year for 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_69eefacbcc2081909ebf00daa23f1981 |
completed | April 27, 2026, 5:57 a.m. |
| NER | Named-entity recognition | batch_69f7979a073881909a4fde2558e6b6f3 |
completed | May 3, 2026, 6:44 p.m. |
| PD | Predicate disambiguation | batch_69f7961550f88190b7bb8a9155458b54 |
completed | May 3, 2026, 6:38 p.m. |
Created at: April 27, 2026, 9:06 a.m.