Triple
T17330296
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lefschetz fibration |
E420794
|
entity |
| Predicate | singularFiberHas |
P3282
|
FINISHED |
| Object | single transverse node |
—
|
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: single transverse node | Statement: [Lefschetz fibration, singularFiberHas, single transverse node]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: singularFiberHas Context triple: [Lefschetz fibration, singularFiberHas, single transverse node]
-
A.
isSingle
Indicates that an entity is not currently in a romantic relationship or legally married.
-
B.
singleWith
Indicates that an entity is unmarried and not currently in a romantic relationship.
-
C.
singularName
Indicates that an entity has a single-item or singular form of its name used to refer to one instance of that entity.
-
D.
hasSingle
chosen
Indicates that an entity possesses exactly one instance of a specified related entity or attribute.
-
E.
singleType
Indicates that an entity belongs to exactly one specific type or category, with no additional types assigned.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e439d5c788819092bdc4d3de0ec958 |
completed | April 19, 2026, 2:11 a.m. |
| PD | Predicate disambiguation | batch_69e3b021a5bc81909ae55406f9d0b37f |
completed | April 18, 2026, 4:24 p.m. |
Created at: April 10, 2026, 5:43 a.m.