Triple
T38532470
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Labor and Employment Law Division |
E923403
|
entity |
| Predicate | employerClient |
P33603
|
FINISHED |
| Object | City of New York |
—
|
NE NERFINISHED |
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: City of New York | Statement: [Labor and Employment Law Division, employerClient, City of New York]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: employerClient Context triple: [Labor and Employment Law Division, employerClient, City of New York]
-
A.
employerOrPrimaryClient
Indicates that one entity serves as the main employer or principal client of another entity in a work or service relationship.
-
B.
employerService
Indicates that one entity provides employment-related services or functions to another entity, typically in the role of an employer.
-
C.
employerIn
chosen
Indicates that one entity serves as the employer of another within a specified context, such as a location, organization, or time period.
-
D.
employerSide
Indicates that the subject participates in or represents the employer’s position, interests, or perspective within an employment relationship or dispute.
-
E.
employerRight
Indicates that an employer holds a specific right, entitlement, or legal authority in relation to an employee or employment situation.
- 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_69f76ea8f6348190a5c03fb6292bbee3 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fd4d1854988190be093b103a681798 |
completed | May 8, 2026, 2:40 a.m. |
| PD | Predicate disambiguation | batch_69fd4c8d1a188190897c24527337814a |
completed | May 8, 2026, 2:38 a.m. |
Created at: May 3, 2026, 4:32 p.m.