Triple
T17148997
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New Jersey Division of Taxation |
E416168
|
entity |
| Predicate | employerFor |
P7
|
FINISHED |
| Object | New Jersey state tax auditors |
—
|
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: New Jersey state tax auditors | Statement: [New Jersey Division of Taxation, employerFor, New Jersey state tax auditors]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employerFor Context triple: [New Jersey Division of Taxation, employerFor, New Jersey state tax auditors]
-
A.
employerIn
Indicates that one entity serves as the employer of another within a specified context, such as a location, organization, or time period.
-
B.
employer
chosen
Indicates a relationship where one entity hires, pays, and oversees the work of another entity.
-
C.
employerSide
Indicates that the subject participates in or represents the employer’s position, interests, or perspective within an employment relationship or dispute.
-
D.
formerEmployer
Indicates that one entity previously employed the other but no longer does so.
-
E.
parentEmployer
Indicates that one organization is the direct or higher-level employer of another organization or entity.
- 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_69d886d279c081909f8ff1f743ddeb69 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3f4059d90819092d3609326fa3130 |
completed | April 18, 2026, 9:13 p.m. |
| PD | Predicate disambiguation | batch_69e3830d2a90819092386717dc56f0e8 |
completed | April 18, 2026, 1:11 p.m. |
Created at: April 10, 2026, 5:36 a.m.