Triple
T25036099
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia Insurance Commissioner |
E626980
|
entity |
| Predicate | hasSubordinateAgency |
P25079
|
FINISHED |
| Object | Office of the State Fire Marshal (Georgia) |
—
|
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: Office of the State Fire Marshal (Georgia) | Statement: [Georgia Insurance Commissioner, hasSubordinateAgency, Office of the State Fire Marshal (Georgia)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubordinateAgency Context triple: [Georgia Insurance Commissioner, hasSubordinateAgency, Office of the State Fire Marshal (Georgia)]
-
A.
numberOfSubordinateAgencies
Indicates the total count of agencies that are hierarchically subordinate to a given parent agency.
-
B.
hasParentAgencyType
Indicates that an agency is associated with or falls under a parent agency of a specified type.
-
C.
hasSubordinateFunction
Indicates that one function operates under the authority, control, or scope of another function as its subordinate.
-
D.
hasSubfacility
Indicates that one facility is a subordinate or component facility within another, larger facility.
-
E.
hasSubsidiaryLabel
chosen
Indicates that one entity is identified as a subsidiary or subordinate organization of another entity.
- 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_69e2ff2a2c088190be513727ee8bfe78 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f60c3b09488190ade1b69ff7f0df0e |
completed | May 2, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69f60b8461ac81908c5bd3d73eed59f4 |
completed | May 2, 2026, 2:34 p.m. |
Created at: April 18, 2026, 6:08 a.m.