Triple
T36871236
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kirby calculus |
E911226
|
entity |
| Predicate | helpsConstruct |
P76723
|
FINISHED |
| Object | handle decompositions of 4-manifolds from framed links |
—
|
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: handle decompositions of 4-manifolds from framed links | Statement: [Kirby calculus, helpsConstruct, handle decompositions of 4-manifolds from framed links]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: helpsConstruct Context triple: [Kirby calculus, helpsConstruct, handle decompositions of 4-manifolds from framed links]
-
A.
helpsBuild
chosen
Indicates that one entity assists or contributes to the construction, creation, or development of another entity.
-
B.
helpsIn
Indicates that one entity provides assistance, support, or aid to another entity in performing or achieving a particular task, activity, or goal.
-
C.
constructs
Indicates that an agent builds, creates, or assembles something, typically resulting in a new or more complex entity or structure.
-
D.
helpsProduce
Indicates that one entity contributes to or facilitates the creation, generation, or production of another entity.
-
E.
helpsDesign
Indicates that one entity assists or contributes to another entity’s design or design process.
- 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_69f76e82339881909607a65c0503d941 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.