Triple
T36498278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jenny Saville |
E899251
|
entity |
| Predicate | careerEvent |
P41295
|
FINISHED |
| Object | was commissioned by Charles Saatchi early in her career |
—
|
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: was commissioned by Charles Saatchi early in her career | Statement: [Jenny Saville, careerEvent, was commissioned by Charles Saatchi early in her career]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: careerEvent Context triple: [Jenny Saville, careerEvent, was commissioned by Charles Saatchi early in her career]
-
A.
careerStation
Indicates the role, position, or stage a person holds within their professional career path.
-
B.
careerThirds
Indicates that one entity has achieved a specified number of third-place finishes over the course of their entire career.
-
C.
careerWalks
Indicates the total number of bases on balls (walks) a player has received over the course of their entire career.
-
D.
careerStart
Indicates the point in time when an entity begins its professional career or main occupational activity.
-
E.
careerTriples
chosen
Indicates a relationship that links an individual to key career-related facts, such as their roles, employers, or professional milestones.
- 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_69f76e5b92088190933afda3f7531dd4 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1b91fd88190ab85afd626603769 |
completed | May 3, 2026, 9:44 p.m. |
Created at: May 3, 2026, 4:10 p.m.