Triple
T37727807
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scott Lynch |
E940069
|
entity |
| Predicate | startedWritingCareer |
P2214
|
FINISHED |
| Object | 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: early 2000s | Statement: [Scott Lynch, startedWritingCareer, early 2000s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: startedWritingCareer Context triple: [Scott Lynch, startedWritingCareer, early 2000s]
-
A.
startedCareerWith
Indicates that an entity began its professional career associated with, employed by, or active for another specified entity.
-
B.
startedStandUpCareerIn
Indicates that an individual began their stand-up comedy career in a particular place or context.
-
C.
startedStandUpCareer
Indicates that an individual began their professional involvement in stand-up comedy at a particular time or event.
-
D.
careerStart
chosen
Indicates the point in time when an entity begins its professional career or main occupational activity.
-
E.
startedSoloCareer
Indicates that an individual began pursuing a professional career independently, separate from any previous group or collaborative affiliation.
- 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_69f76edefd048190a32212c5c3919531 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_6a013a251b4081908b43d85dd95586c5 |
completed | May 11, 2026, 2:08 a.m. |
| PD | Predicate disambiguation | batch_6a0137e4ea988190812173a5ff044098 |
completed | May 11, 2026, 1:59 a.m. |
Created at: May 3, 2026, 4:18 p.m.