Triple
T31412103
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kendrick Kang-Joh Jeong |
E801294
|
entity |
| Predicate | yearsActiveAsEntertainer |
P153766
|
FINISHED |
| Object | 1990s–present |
—
|
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–present | Statement: [Kendrick Kang-Joh Jeong, yearsActiveAsEntertainer, 1990s–present]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearsActiveAsEntertainer Context triple: [Kendrick Kang-Joh Jeong, yearsActiveAsEntertainer, 1990s–present]
-
A.
performingSince
chosen
Indicates that an entity has been actively performing a particular activity or role starting from a specified point in time.
-
B.
activeYearsInFilm
Indicates the span of years during which an entity was actively involved in film-related work or roles.
-
C.
timeInArtistCareer
Indicates the point or period within an artist’s professional career at which a given event, work, or activity occurs.
-
D.
yearsActiveInStory
Indicates the span of years during which the entity is active or participates within the context of the story.
-
E.
activeYearsInPornography
Indicates the span of years during which an individual was actively working in the pornography industry.
- 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_69f348c0dd648190bf2fd7642f78eb06 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6a5f71b2c8190aade8a83f465be0c |
completed | May 3, 2026, 1:33 a.m. |
| PD | Predicate disambiguation | batch_69f69fe66df08190958558d63ee623d9 |
completed | May 3, 2026, 1:07 a.m. |
Created at: April 30, 2026, 8:39 p.m.