Triple
T20851760
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feferman–Schütte ordinal |
E513379
|
entity |
| Predicate | isStrictlyLessThan |
P11452
|
FINISHED |
| Object | Bachmann–Howard ordinal |
—
|
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: Bachmann–Howard ordinal | Statement: [Feferman–Schütte ordinal, isStrictlyLessThan, Bachmann–Howard ordinal]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isStrictlyLessThan Context triple: [Feferman–Schütte ordinal, isStrictlyLessThan, Bachmann–Howard ordinal]
-
A.
lessExclusiveThan
Indicates that one entity has a broader or more inclusive scope, membership, or applicability than another, which is more exclusive.
-
B.
variesLessThan
Indicates that the degree or amount of change in one quantity is smaller than the degree or amount of change in another quantity.
-
C.
isHigherThan
Indicates that one entity has a greater value, level, or position than another entity.
-
D.
smallerThan
chosen
Indicates that one entity has a strictly lesser size, dimension, or magnitude than another entity.
-
E.
lessThanOrEqualTo
Indicates that one entity’s value is smaller than or exactly equal to another entity’s value.
- 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_69e0b4f4898081908209e58edb8f9c45 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c3a3d8808190b8efce77ae36850e |
completed | April 21, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69e5c9a593f481908beb457c29f1ce73 |
completed | April 20, 2026, 6:37 a.m. |
Created at: April 16, 2026, 12:43 p.m.