Triple
T21953535
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ehresmann connection |
E542125
|
entity |
| Predicate | splits |
P146683
|
FINISHED |
| Object | tangent bundle of the total space of a fiber bundle |
—
|
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: tangent bundle of the total space of a fiber bundle | Statement: [Ehresmann connection, splits, tangent bundle of the total space of a fiber bundle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: splits Context triple: [Ehresmann connection, splits, tangent bundle of the total space of a fiber bundle]
-
A.
separates
Indicates that one entity divides, parts, or keeps other entities apart from each other.
-
B.
commonSplit
Indicates that multiple entities share a common point or manner of division into parts.
-
C.
typicalSplit
Indicates that something is divided into parts or portions in the usual or most common way.
-
D.
splitWith
Indicates that one entity divides or shares something with another entity.
-
E.
factionSplit
Indicates that a previously unified group has divided into separate, often opposing, factions.
- F. None of above. chosen
Provenance (4 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_69e0c47ef0e48190a50e1bcc43f4b3fd |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f1243dfb4081909bc7a722843ffea7 |
completed | April 28, 2026, 9:18 p.m. |
| PD | Predicate disambiguation | batch_69e6f601f2188190893bcdde0cf58ad6 |
completed | April 21, 2026, 3:58 a.m. |
| PDg | Predicate description generation | batch_69e6fb9b75308190addc3dba7b5d5ddd |
completed | April 21, 2026, 4:22 a.m. |
Created at: April 16, 2026, 7:59 p.m.