Triple
T3488118
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ideal gas law |
E73657
|
entity |
| Predicate | constantTypicalValue |
P3644
|
FINISHED |
| Object | 8.314 J·mol⁻¹·K⁻¹ |
—
|
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: 8.314 J·mol⁻¹·K⁻¹ | Statement: [ideal gas law, constantTypicalValue, 8.314 J·mol⁻¹·K⁻¹]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: constantTypicalValue Context triple: [ideal gas law, constantTypicalValue, 8.314 J·mol⁻¹·K⁻¹]
-
A.
constant
chosen
Indicates that the relationship or value does not change across different instances, contexts, or over time.
-
B.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
C.
typicalConsistency
Indicates that one entity characteristically maintains a regular or expected level of consistency in relation to another entity or context.
-
D.
typicalRange
Indicates the usual or expected range of values, conditions, or states within which something normally occurs or applies.
-
E.
typicalKey
Indicates that the referenced key is the standard or most commonly used key associated with an entity or context.
- 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_69ad85cca8d4819088494e9f3340fab5 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbb9193688190aa0cbf87a7b99446 |
completed | March 8, 2026, 6:10 p.m. |
| PD | Predicate disambiguation | batch_69adae0b34908190b2bb5766a2231f7a |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:18 p.m.