Triple
T30728554
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tani Rey |
E782349
|
entity |
| Predicate | recruitStatus |
P133905
|
FINISHED |
| Object | former police academy recruit |
—
|
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: former police academy recruit | Statement: [Tani Rey, recruitStatus, former police academy recruit]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recruitStatus Context triple: [Tani Rey, recruitStatus, former police academy recruit]
-
A.
hasRecruitStatus
chosen
Indicates that an entity holds a particular recruitment-related status or stage within a recruiting process.
-
B.
ResumeStatus
Indicates the current state or condition of a resume within a review or processing workflow.
-
C.
applicantState
Indicates the current status or condition assigned to an applicant within a process or system.
-
D.
applicantStates
Indicates that an applicant explicitly declares or asserts a particular fact, condition, or piece of information.
-
E.
canBeRecruitedFrom
Indicates that one entity is eligible to be recruited, obtained, or enlisted starting from or via another specified entity or source.
- 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_69f224ad9f9c81908e02a79ae0001137 |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f68ee186508190894808b23be1d88d |
completed | May 2, 2026, 11:55 p.m. |
| PD | Predicate disambiguation | batch_69f6861170d08190bb98be609d436f84 |
completed | May 2, 2026, 11:17 p.m. |
Created at: April 29, 2026, 8:37 p.m.