Triple
T624673
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Alexis de Tocqueville |
E14589
|
entity |
| Predicate | travelPurpose |
P79
|
FINISHED |
| Object | study of the American prison system |
—
|
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: study of the American prison system | Statement: [Alexis de Tocqueville, travelPurpose, study of the American prison system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: travelPurpose Context triple: [Alexis de Tocqueville, travelPurpose, study of the American prison system]
-
A.
travelPreference
Indicates a person's favored way or style of traveling, such as preferred modes, conditions, or arrangements for trips.
-
B.
travelsOn
Indicates that an entity moves or journeys using a particular route, path, or mode of transportation.
-
C.
purpose
chosen
Indicates that one entity exists, is done, or is used in order to achieve, support, or serve the goal, function, or intended outcome of another entity.
-
D.
involvedTravelBetween
Indicates a relationship where an entity participates in or is associated with travel occurring between two specified locations.
-
E.
tourismType
Indicates the specific category or kind of tourism activity or experience associated with an entity.
- 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_69a4934b17c881909ace8270e8ddd202 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49e43002c81908e0c7dab29b75978 |
completed | March 1, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69a49d0069d0819087c83b608f6fc053 |
completed | March 1, 2026, 8:09 p.m. |
Created at: March 1, 2026, 7:35 p.m.