Triple
T15235532
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Boston Federal Reserve District |
E364116
|
entity |
| Predicate | servesPartOfState |
P117679
|
FINISHED |
| Object | northern Connecticut |
—
|
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: northern Connecticut | Statement: [Boston Federal Reserve District, servesPartOfState, northern Connecticut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: servesPartOfState Context triple: [Boston Federal Reserve District, servesPartOfState, northern Connecticut]
-
A.
servesStateOrDistrict
Indicates that an entity holds a role or position in service to a specific state or electoral district.
-
B.
servesStateCapitalRegion
Indicates that an entity provides services or functions as a service hub for the state capital region.
-
C.
participatingState
Indicates that a state is taking part in, or is formally involved as a participant in, a specified event, process, or arrangement.
-
D.
representedState
Indicates that one entity serves as a representation or depiction of the state or condition of another entity.
-
E.
servesProvince
Indicates that one entity (typically an organization, service, or administrative unit) provides service or has jurisdiction over a specified province.
- 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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e007d91e4881908ea52d11a3d4480a |
completed | April 15, 2026, 9:49 p.m. |
| PD | Predicate disambiguation | batch_69deca899d5c8190be4a7c71e1683c69 |
completed | April 14, 2026, 11:15 p.m. |
| PDg | Predicate description generation | batch_69decf2ca6148190967c319728ec3661 |
completed | April 14, 2026, 11:35 p.m. |
Created at: April 10, 2026, 3:12 a.m.