Triple
T23624733
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lipton–Tarjan separator theorem |
E583430
|
entity |
| Predicate | graphClass |
P96954
|
FINISHED |
| Object | undirected graphs |
—
|
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: undirected graphs | Statement: [Lipton–Tarjan separator theorem, graphClass, undirected graphs]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: graphClass Context triple: [Lipton–Tarjan separator theorem, graphClass, undirected graphs]
-
A.
graphAnalogue
Indicates that one entity serves as a graph-theoretic counterpart or structural analogue of another entity.
-
B.
usesGraphType
chosen
Indicates that one entity employs or is configured to operate with a specific type of graph representation or graph model.
-
C.
graphNameCanBe
Indicates that a graph is allowed to take on or be assigned a specified name.
-
D.
depictsClass
Indicates that one entity visually represents or portrays a particular class or category of entities.
-
E.
dependencyGraph
Indicates a relationship where one entity’s existence, behavior, or outcome depends on one or more other entities, forming a structured network of such dependencies.
- 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_69e248fc8d74819091bd5baef2f36f6f |
completed | April 17, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69f1b17be6288190a409df700c1003bd |
completed | April 29, 2026, 7:21 a.m. |
| PD | Predicate disambiguation | batch_69f118d0e0588190a86527a7747c5427 |
completed | April 28, 2026, 8:30 p.m. |
Created at: April 17, 2026, 6:46 p.m.