Triple
T23118012
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | environmental law clinic |
E576810
|
entity |
| Predicate | legalServiceType |
P6527
|
FINISHED |
| Object | public interest law |
—
|
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: public interest law | Statement: [environmental law clinic, legalServiceType, public interest law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legalServiceType Context triple: [environmental law clinic, legalServiceType, public interest law]
-
A.
typeOfLaw
chosen
Indicates that one entity is a specific category or kind of law to which the other entity pertains.
-
B.
legalTestType
Indicates the specific kind or category of legal test or standard that is applied in a given legal context or proceeding.
-
C.
legalCodeFocus
Indicates that something is specifically concerned with, centered on, or primarily addressing a particular legal code or body of law.
-
D.
legalRepresentation
Indicates that one entity formally acts on behalf of another in legal matters, such as providing counsel, advocacy, or defense within a legal system.
-
E.
legalTool
Indicates a relationship where something functions as a legal instrument, mechanism, or means used to achieve or regulate a legal purpose or outcome.
- 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_69e245f6c2e881909a228fdcfeb7c7d3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18e4dd7d8819087cc50b2dc94798e |
completed | April 29, 2026, 4:51 a.m. |
| PD | Predicate disambiguation | batch_69ef89f020588190b43393e048e7eda3 |
completed | April 27, 2026, 4:08 p.m. |
Created at: April 17, 2026, 3:59 p.m.