Triple
T4842977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | City of New York |
E108219
|
entity |
| Predicate | hasPolicyDomain |
P7262
|
FINISHED |
| Object | maritime commerce |
—
|
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: maritime commerce | Statement: [City of New York, hasPolicyDomain, maritime commerce]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPolicyDomain Context triple: [City of New York, hasPolicyDomain, maritime commerce]
-
A.
hasPolicySupport
Indicates that one entity provides endorsement, backing, or approval for a specific policy associated with another entity.
-
B.
hasPolicyArea
chosen
Indicates that an entity (such as a policy, program, or initiative) is associated with or pertains to a specific policy area or domain.
-
C.
hasKeyPolicy
Indicates that an entity is associated with a specific key management or access control policy governing how its keys may be used or managed.
-
D.
hasReferencePolicy
Indicates that an entity is governed by or associated with a specific reference policy that defines how it should be used, accessed, or managed.
-
E.
hasLanguagePolicyContext
Indicates that there is an associated language-related policy, rule, or regulatory context governing how language is used or managed in relation to the subject.
- 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_69bd4409b264819085ab855f3eb5381a |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6e01872c81909607010c10538ad1 |
completed | March 20, 2026, 3:55 p.m. |
| PD | Predicate disambiguation | batch_69bd6c2375a4819098e16acb982c8fab |
completed | March 20, 2026, 3:47 p.m. |
Created at: March 20, 2026, 1:25 p.m.