Triple
T3866259
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Queens Boulevard |
E91860
|
entity |
| Predicate | sawPolicyChange |
P51559
|
FINISHED |
| Object | installation of pedestrian safety measures |
—
|
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: installation of pedestrian safety measures | Statement: [Queens Boulevard, sawPolicyChange, installation of pedestrian safety measures]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sawPolicyChange Context triple: [Queens Boulevard, sawPolicyChange, installation of pedestrian safety measures]
-
A.
changePolicy
Indicates that an entity modifies, replaces, or updates an existing policy governing rules, procedures, or behaviors.
-
B.
securityChangesAfter
Indicates that the security status or configuration of one entity is modified as a consequence of a prior event or change in another entity.
-
C.
sawServicePeriod
Indicates that one entity observed or was aware of the duration or specific period during which a service was provided or active.
-
D.
implementedPolicy
Indicates that a particular policy has been put into effect or carried out by an entity.
-
E.
scriptChangePolicy
Indicates a policy governing when, how, or under what conditions a script may be modified or updated.
- F. None of above. chosen
Provenance (4 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_69aed9645f348190a9868e7cef56ab7e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aeec3b8d988190b56d42ac1521e19c |
completed | March 9, 2026, 3:50 p.m. |
| PD | Predicate disambiguation | batch_69aee754dddc8190936e1f9c40a770db |
completed | March 9, 2026, 3:29 p.m. |
| PDg | Predicate description generation | batch_69aee80858a481909961a33fb50ff8d1 |
completed | March 9, 2026, 3:32 p.m. |
Created at: March 9, 2026, 3:19 p.m.