Triple
T38099368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steve Sullivan |
E951333
|
entity |
| Predicate | leavesJobFor |
P15987
|
FINISHED |
| Object | running family bar |
—
|
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: running family bar | Statement: [Steve Sullivan, leavesJobFor, running family bar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: leavesJobFor Context triple: [Steve Sullivan, leavesJobFor, running family bar]
-
A.
leavesEmployer
Indicates that an employee ends or terminates their working relationship with an employer.
-
B.
leavesJobType
Indicates that an entity stops or departs from a particular type or category of job or employment.
-
C.
resignsFrom
Indicates that an entity voluntarily leaves or gives up a position, role, or membership in another entity.
-
D.
reasonForLeaving
chosen
Indicates the cause, motivation, or circumstance that led an entity to depart or discontinue an association, position, or place.
-
E.
leaveType
Indicates the type or category of leave associated with an absence or time-off event (e.g., vacation, sick leave, parental leave).
- 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_69f76f04960c8190a83f14ae4c67f5bc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.