Triple
T11701123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | James Glaisher |
E278124
|
entity |
| Predicate | madeObservation |
P36943
|
FINISHED |
| Object | temperature variation with altitude |
—
|
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: temperature variation with altitude | Statement: [James Glaisher, madeObservation, temperature variation with altitude]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: madeObservation Context triple: [James Glaisher, madeObservation, temperature variation with altitude]
-
A.
hasObservation
Indicates that an entity records, contains, or is associated with a specific observation or measured instance.
-
B.
observation
chosen
Indicates that one entity perceives, monitors, or takes note of another entity or phenomenon, typically to gather information about it.
-
C.
observationNote
Indicates that there is an associated free-text comment or remark providing additional details or context about an observation.
-
D.
observationType
Indicates the specific kind or category of observation being made or recorded in a given context.
-
E.
mayObserve
Indicates that one entity is permitted or allowed to observe, monitor, or watch another entity or process.
- 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_69d6aafe02d881909900d54ad7d4af84 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a49a025881909377c81d3debf465 |
completed | April 10, 2026, 7:19 a.m. |
| PD | Predicate disambiguation | batch_69d88a7b30948190b616a9db5c5488d5 |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:40 p.m.