Triple
T3698688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amstel Gold Race |
E78519
|
entity |
| Predicate | finishingStyle |
P14336
|
FINISHED |
| Object | uphill or slightly uphill sprint |
—
|
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: uphill or slightly uphill sprint | Statement: [Amstel Gold Race, finishingStyle, uphill or slightly uphill sprint]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: finishingStyle Context triple: [Amstel Gold Race, finishingStyle, uphill or slightly uphill sprint]
-
A.
typicalFinish
Indicates that an action, process, or event commonly or characteristically ends with a particular outcome or state.
-
B.
interiorStyle
Indicates that one entity has a particular interior design style or aesthetic characterized by the other entity.
-
C.
finishingArea
Indicates the location or area where an activity, process, or event comes to an end or is completed.
-
D.
furnishingType
Indicates the type or category of furnishings associated with an entity, such as a property or room.
-
E.
endingStyle
chosen
Indicates the manner or stylistic form in which something concludes or is brought to an end.
- 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_69ad85e3b1888190abc983e06968696d |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc512ba188190a15bcacafac3f476 |
completed | March 8, 2026, 6:50 p.m. |
| PD | Predicate disambiguation | batch_69adb84dc5808190850aa6975cb09e27 |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:26 p.m.