Triple
T36468620
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fenchel–Nielsen coordinates |
E898483
|
entity |
| Predicate | lengthParameterRepresents |
P266
|
FINISHED |
| Object | hyperbolic length of a simple closed geodesic |
—
|
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: hyperbolic length of a simple closed geodesic | Statement: [Fenchel–Nielsen coordinates, lengthParameterRepresents, hyperbolic length of a simple closed geodesic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lengthParameterRepresents Context triple: [Fenchel–Nielsen coordinates, lengthParameterRepresents, hyperbolic length of a simple closed geodesic]
-
A.
parameterLRepresentation
Indicates that one entity serves as the L-representation (e.g., a specific formal or linguistic representation) of a parameter associated with another entity.
-
B.
identifierLength
Indicates the length or number of characters in an entity’s identifier.
-
C.
extensionLength
Indicates the length or magnitude of an extension from a reference point or base object.
-
D.
basePathLength
Indicates the length of the primary or reference path used as a baseline in a given context.
-
E.
length
chosen
Indicates a measurement relationship where a value specifies how long something is from one end to the other.
- 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_69f76e58ebd88190b75d9b169b59d793 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7be9d07ac8190adf796cbef60daf6 |
completed | May 3, 2026, 9:31 p.m. |
| PD | Predicate disambiguation | batch_69f7bccf05bc8190b61fdb2b2a315811 |
completed | May 3, 2026, 9:23 p.m. |
Created at: May 3, 2026, 4:10 p.m.