Triple
T18509326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tonya Harding |
E452291
|
entity |
| Predicate | enteredProfession |
P124115
|
FINISHED |
| Object | professional boxing in the early 2000s |
—
|
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: professional boxing in the early 2000s | Statement: [Tonya Harding, enteredProfession, professional boxing in the early 2000s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: enteredProfession Context triple: [Tonya Harding, enteredProfession, professional boxing in the early 2000s]
-
A.
hasGivenProfession
chosen
Indicates that an entity holds or practices a specified profession or occupation.
-
B.
leftProfession
Indicates that an entity has stopped or abandoned a particular profession or occupation they previously held.
-
C.
managedCareerOf
Indicates that one entity was responsible for overseeing, directing, or handling the professional career of another entity.
-
D.
employedAfter
Indicates that one entity became employed by another entity at a point in time later than a referenced employment event or period.
-
E.
startedCareerWith
Indicates that an entity began its professional career associated with, employed by, or active for another specified 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_69d8d386df84819092355ebb260d848e |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e53344c6b081908e780ed5c815a766 |
completed | April 19, 2026, 7:55 p.m. |
| PD | Predicate disambiguation | batch_69e469dbf5208190b6fc49e02a087f54 |
completed | April 19, 2026, 5:36 a.m. |
Created at: April 10, 2026, 11:36 a.m.