Triple
T37140973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Affinity Water |
E920106
|
entity |
| Predicate | operatesUnderLicenceFrom |
P79282
|
FINISHED |
| Object | Ofwat |
E549362
|
NE 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: Ofwat | Statement: [Affinity Water, operatesUnderLicenceFrom, Ofwat]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operatesUnderLicenceFrom Context triple: [Affinity Water, operatesUnderLicenceFrom, Ofwat]
-
A.
operatedUnderLicenseFrom
chosen
Indicates that one entity conducts its activities or uses certain rights with formal permission granted by another entity that holds the original authority or ownership.
-
B.
operatesUnderName
Indicates that an entity conducts its activities or business using a particular name, which may differ from its official or legal name.
-
C.
operatesUnderFranchiseFrom
Indicates that one entity conducts its business or operations under the franchising rights, brand, and system granted by another entity.
-
D.
servesAsOperatorOf
Indicates that one entity functions as the operator or operating agent responsible for running, controlling, or managing another entity.
-
E.
licenceAuthority
Indicates that one entity has the official power or jurisdiction to grant, issue, or regulate licences for another entity or activity.
- F. None of above.
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_69f76e9e9d008190a250b0387c992c74 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a0205c0bff481908238a382459b3a93 |
completed | May 11, 2026, 4:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a402baa701481909f0accc10a5f8f0c |
completed | June 27, 2026, 7:59 p.m. |
| PD | Predicate disambiguation | batch_6a0205143f20819087ee31576835be26 |
completed | May 11, 2026, 4:34 p.m. |
Created at: May 3, 2026, 4:15 p.m.