Triple
T25073683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pontryagin classes |
E627990
|
entity |
| Predicate | zeroFor |
P9150
|
FINISHED |
| Object | all bundles over a point |
—
|
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: all bundles over a point | Statement: [Pontryagin classes, zeroFor, all bundles over a point]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: zeroFor Context triple: [Pontryagin classes, zeroFor, all bundles over a point]
-
A.
isZeroFor
chosen
Indicates that a given value, expression, or function evaluates to zero when applied to or considered with respect to a specified entity or context.
-
B.
zeroDefinition
Indicates that something has no defined value, quantity, or specification within the given context.
-
C.
formsZeroPointFor
Indicates that one entity serves as the reference or origin point (zero point) for measuring or defining another entity.
-
D.
zeroConcept
Indicates a conceptual or abstract entity that has no concrete instances or realizations in the given context.
-
E.
noPointsFor
Indicates that an entity receives no credit, score, or reward as a result of a particular action, condition, or outcome.
- 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_69e2ff2d71dc8190b4758e57d643cbe4 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f45d177c3881909ac5058e3e866d93 |
completed | May 1, 2026, 7:58 a.m. |
| PD | Predicate disambiguation | batch_69f442c861188190967655c6d8012380 |
completed | May 1, 2026, 6:06 a.m. |
Created at: April 18, 2026, 6:19 a.m.