Triple
T7188615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | kelvin |
E167630
|
entity |
| Predicate | previousDefinitionBasedOn |
P33255
|
FINISHED |
| Object | triple point of water |
—
|
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: triple point of water | Statement: [kelvin, previousDefinitionBasedOn, triple point of water]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousDefinitionBasedOn Context triple: [kelvin, previousDefinitionBasedOn, triple point of water]
-
A.
previouslyBasedOn
Indicates that something was formerly derived from, adapted from, or dependent on another source, but is no longer based on it in its current state.
-
B.
laterDefinedBy
Indicates that the referenced entity’s full definition or specification is provided at a subsequent point in the same or another resource.
-
C.
replacedDefinitionOf
Indicates that one definition or description has been superseded and taken the place of another.
-
D.
previouslyDefinedIn
chosen
Indicates that something has been defined or introduced earlier in time or in a prior context relative to the current reference point.
-
E.
isBasedOn
Indicates that one entity is derived from, inspired by, or developed using the content, structure, or principles 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_69c6888b5248819090499a884ee3ec39 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e8e3d9188190ba2792098d76fb86 |
completed | March 27, 2026, 8:30 p.m. |
| PD | Predicate disambiguation | batch_69c6e752385c819096fbab55566ee2a8 |
completed | March 27, 2026, 8:23 p.m. |
Created at: March 27, 2026, 2:50 p.m.