Triple
T3456114
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clásica de San Sebastián |
E72907
|
entity |
| Predicate | startFinishType |
P48334
|
FINISHED |
| Object | loop course |
—
|
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: loop course | Statement: [Clásica de San Sebastián, startFinishType, loop course]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startFinishType Context triple: [Clásica de San Sebastián, startFinishType, loop course]
-
A.
startFinishArea
Indicates a relationship where a defined area serves as both the starting point and the finishing point for an event, route, or activity.
-
B.
starterType
Indicates the classification or category of a starter (e.g., initial component, opening item, or first phase) associated with an entity or process.
-
C.
raceStartType
Indicates the manner or format in which a race is initiated (e.g., type or method of starting the race).
-
D.
finalStep
Indicates that an action or state represents the last step or concluding stage in a process or sequence.
-
E.
hasStopType
Indicates that a stop or stopping point is classified as having a particular type or category of stop.
- 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_69ad85b12a908190a1d10a6b03b4f8ae |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adbaa77b9c81909376a5995cdaf6ac |
completed | March 8, 2026, 6:06 p.m. |
| PD | Predicate disambiguation | batch_69adae041d588190a84a02bca94adec8 |
completed | March 8, 2026, 5:12 p.m. |
| PDg | Predicate description generation | batch_69adaed74ecc8190b74dc70ab59a3e1c |
completed | March 8, 2026, 5:16 p.m. |
Created at: March 8, 2026, 3:16 p.m.