Triple
T29836682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regional Transport Offices in Kerala |
E757674
|
entity |
| Predicate | hasSubAgencyType |
P38626
|
FINISHED |
| Object | Regional Transport Office (RTO) |
—
|
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: Regional Transport Office (RTO) | Statement: [Regional Transport Offices in Kerala, hasSubAgencyType, Regional Transport Office (RTO)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSubAgencyType Context triple: [Regional Transport Offices in Kerala, hasSubAgencyType, Regional Transport Office (RTO)]
-
A.
hasParentAgencyType
Indicates that an agency is associated with or falls under a parent agency of a specified type.
-
B.
hasSubOrganizationType
chosen
Indicates that an organization is associated with or classified under a specific type or category of sub-organization.
-
C.
isAgencyType
Indicates that an entity belongs to, or is classified under, a particular type or category of agency.
-
D.
hasMunicipalAgencyType
Indicates that a municipal agency is classified as having a specific organizational or functional type.
-
E.
hasSubsidiaryLabel
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_69f224593f6c81908785a560fe659f58 |
completed | April 29, 2026, 3:31 p.m. |
| NER | Named-entity recognition | batch_69fde5d7d9548190880a9d95b8f0f66b |
completed | May 8, 2026, 1:32 p.m. |
| PD | Predicate disambiguation | batch_69fde4e1bf9c81909754545275eccc03 |
completed | May 8, 2026, 1:28 p.m. |
Created at: April 29, 2026, 5:37 p.m.