Triple
T23902530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sakata model |
E601091
|
entity |
| Predicate | fundamentalConstituentsCalled |
P14960
|
FINISHED |
| Object | baryons |
—
|
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: baryons | Statement: [Sakata model, fundamentalConstituentsCalled, baryons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fundamentalConstituentsCalled Context triple: [Sakata model, fundamentalConstituentsCalled, baryons]
-
A.
numberOfConstituents
Indicates the total count of individual components or members that make up a larger whole or group.
-
B.
constitutedBy
chosen
Indicates that something is made up of, composed from, or formed by the specified parts or elements.
-
C.
usesConstituentsFrom
Indicates that one entity is composed of, incorporates, or is derived from specific constituent parts provided by another entity.
-
D.
potentialConstituentsOf
Indicates that the related entities are possible members or components that could form part of a larger whole or structure.
-
E.
typicalConstituentType
Indicates the usual or characteristic type of component that typically makes up or forms part of something.
- 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_69e295364a488190bcac702e9bb7f764 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cddf46948190b8625811725fe41d |
completed | April 29, 2026, 9:22 a.m. |
| PD | Predicate disambiguation | batch_69f1614e24b48190a1c8fb5b7c75ee0f |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:26 p.m.