Triple
T19956997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kate’s Cottage |
E479709
|
entity |
| Predicate | onRacingSection |
P55669
|
FINISHED |
| Object | mountain section of Snaefell Mountain 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: mountain section of Snaefell Mountain Course | Statement: [Kate’s Cottage, onRacingSection, mountain section of Snaefell Mountain Course]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: onRacingSection Context triple: [Kate’s Cottage, onRacingSection, mountain section of Snaefell Mountain Course]
-
A.
raceTrack
Indicates that one entity serves as a race track or racing course used by another entity for racing activities.
-
B.
racecourseFeature
chosen
Indicates that one entity is a physical or functional feature or component of a racecourse associated with the other entity.
-
C.
racingDivision
Indicates that one entity is classified into, or associated with, a particular racing division within a competitive racing context.
-
D.
racingSeries
Indicates that one entity is a racing series in which the other entity (such as a race, team, or driver) participates or to which it belongs.
-
E.
racesOn
Indicates that one entity participates in a race or competitive running event that takes place on or along another entity (such as a track, course, or surface).
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65af08e008190a3a1b807b638a99e |
completed | April 20, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_69e537f7e4848190b431a69ec3f1b609 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.