Triple
T12597457
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | classical fourth-order Runge–Kutta method |
E300768
|
entity |
| Predicate | definesK1As |
P773
|
FINISHED |
| Object | k1 = f(t_n, y_n) |
—
|
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: k1 = f(t_n, y_n) | Statement: [classical fourth-order Runge–Kutta method, definesK1As, k1 = f(t_n, y_n)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: definesK1As Context triple: [classical fourth-order Runge–Kutta method, definesK1As, k1 = f(t_n, y_n)]
-
A.
isKICOf
Indicates that one entity is the Kepler Input Catalog (KIC) identifier or entry corresponding to another astronomical object.
-
B.
keyTerm
Indicates that a term functions as a primary or central concept within a given context or information structure.
-
C.
defined
chosen
Indicates that one entity specifies, explains, or establishes the meaning, scope, or identity of another entity.
-
D.
firstDefinedBy
Indicates that one entity is the original source that formally introduced, specified, or defined another entity.
-
E.
knownAsOneOf
Indicates that an entity is recognized or referred to as one member of a specified set of alternative names, labels, or identities.
- 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_69d7bdea2ca881908f379526c13b1145 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d954e6e20481908bca684c4b497c48 |
completed | April 10, 2026, 7:52 p.m. |
| PD | Predicate disambiguation | batch_69d95416cbd88190b2c65196162349bc |
completed | April 10, 2026, 7:48 p.m. |
Created at: April 9, 2026, 5:08 p.m.