Triple
T26746240
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brooklyn and Staten Island |
E674409
|
entity |
| Predicate | shareAreaOfLaw |
P39225
|
FINISHED |
| Object | New York City Administrative Code |
—
|
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: New York City Administrative Code | Statement: [Brooklyn and Staten Island, shareAreaOfLaw, New York City Administrative Code]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shareAreaOfLaw Context triple: [Brooklyn and Staten Island, shareAreaOfLaw, New York City Administrative Code]
-
A.
sharesLaw
chosen
Indicates that two or more entities are governed by, subject to, or operate under the same law or legal framework.
-
B.
notableAreaOfLaw
Indicates that a person or entity is particularly recognized or distinguished in a specific field or area of law.
-
C.
branchOfLaw
Indicates a relationship where one legal field or discipline is a subdivision or specialized area within a broader body of law.
-
D.
legalArea
Indicates the specific field or branch of law that a legal matter, case, or document pertains to.
-
E.
lawLibrary
Indicates a relationship where a location or resource functions as a library specifically dedicated to legal materials, services, or research.
- 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_69eecda63a3881908095c47900692e65 |
completed | April 27, 2026, 2:44 a.m. |
| NER | Named-entity recognition | batch_69fcab6e888881908ca9e18660928a40 |
completed | May 7, 2026, 3:10 p.m. |
| PD | Predicate disambiguation | batch_69fc4562a5b88190bad48f083a6dcdfa |
completed | May 7, 2026, 7:55 a.m. |
Created at: April 27, 2026, 3:51 a.m.