Triple
T1105481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mila Kunis |
E25478
|
entity |
| Predicate | startOfCareer |
P2214
|
FINISHED |
| Object | 1990s |
—
|
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: 1990s | Statement: [Mila Kunis, startOfCareer, 1990s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startOfCareer Context triple: [Mila Kunis, startOfCareer, 1990s]
-
A.
careerStart
chosen
Indicates the point in time when an entity begins its professional career or main occupational activity.
-
B.
launchedCareerOf
Indicates that one entity’s actions, support, or involvement initiated or significantly advanced another entity’s professional career.
-
C.
partOfCareer
Indicates that one entity represents a role, position, or period that forms a component or phase within another entity’s overall career.
-
D.
occupationBegan
Indicates the point in time when an entity started holding a particular occupation or job.
-
E.
laterCareer
Indicates that the associated information or events pertain to a later stage or phase in an entity’s professional life or career trajectory.
- 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_69a49428d4448190b3b36991ceae87ce |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4b9e21f048190bf4b63dd2c7c7641 |
completed | March 1, 2026, 10:12 p.m. |
| PD | Predicate disambiguation | batch_69a4b74877748190b78cd8847ee4fa7a |
completed | March 1, 2026, 10:01 p.m. |
Created at: March 1, 2026, 7:43 p.m.