Triple
T25130989
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | K_J |
E629520
|
entity |
| Predicate | isExactIn |
P74393
|
FINISHED |
| Object | revised SI based on fixed e and h |
—
|
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: revised SI based on fixed e and h | Statement: [K_J, isExactIn, revised SI based on fixed e and h]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isExactIn Context triple: [K_J, isExactIn, revised SI based on fixed e and h]
-
A.
isExactSince
Indicates that a condition, state, or relationship has held precisely from a specific starting time onward, with that start time being exact rather than approximate.
-
B.
isExactInSI
chosen
Indicates that a quantity or value is defined as an exact, non-approximate value within the International System of Units (SI).
-
C.
holdsExactlyIn
Indicates that a condition, property, or relationship is true only within a specified context, interval, or scope and not beyond it.
-
D.
supportsExactMatch
Indicates that one entity fully upholds or is compatible with another entity only when there is an exact, unaltered match between them.
-
E.
constantExactness
Indicates that a value or relationship holds with complete, unvarying precision, without any approximation or deviation.
- 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_69e2ff338250819096ff6c8892804389 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f465f79bd081909a2f5165aa89dc16 |
completed | May 1, 2026, 8:36 a.m. |
| PD | Predicate disambiguation | batch_69f44d8043b081908bbffd7f044b4f26 |
completed | May 1, 2026, 6:51 a.m. |
Created at: April 18, 2026, 6:28 a.m.