Triple
T31308461
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | New York State Human Rights Law |
E798396
|
entity |
| Predicate | allowsRemedies |
P273
|
FINISHED |
| Object | back pay |
—
|
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: back pay | Statement: [New York State Human Rights Law, allowsRemedies, back pay]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: allowsRemedies Context triple: [New York State Human Rights Law, allowsRemedies, back pay]
-
A.
hasRemedy
Indicates that one entity serves as a remedy, treatment, or corrective measure for a problem, condition, or undesirable state associated with another entity.
-
B.
allows
chosen
Indicates that one entity grants permission, capability, or opportunity for another entity to perform an action or be in a certain state.
-
C.
hasRemediationStatus
Indicates the current state or progress of remediation efforts applied to an identified issue, risk, or non-compliance.
-
D.
remedy
Indicates that one entity serves to cure, alleviate, or counteract a problem, illness, or undesirable condition affecting another entity.
-
E.
excludedRemedy
Indicates that a particular remedy or course of action is specifically ruled out or not permitted within a given agreement, policy, or context.
- 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_69f224e0bd4c8190aab9b29a73f7aa3c |
completed | April 29, 2026, 3:33 p.m. |
| NER | Named-entity recognition | batch_69f7b5ccbda481908fe1945c35e36ce8 |
completed | May 3, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c06f5881908f0b98cad6796478 |
completed | May 3, 2026, 8:49 p.m. |
Created at: April 29, 2026, 9:14 p.m.