Triple
T25099597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sunbury Weir |
E628685
|
entity |
| Predicate | regulatesFlowNear |
P165297
|
FINISHED |
| Object | Sunbury-on-Thames |
—
|
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: Sunbury-on-Thames | Statement: [Sunbury Weir, regulatesFlowNear, Sunbury-on-Thames]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: regulatesFlowNear Context triple: [Sunbury Weir, regulatesFlowNear, Sunbury-on-Thames]
-
A.
regulatesFlowFor
Indicates that one entity controls, directs, or manages the rate or movement of another entity’s flow.
-
B.
regulatesFlowBetween
Indicates a relationship where one entity controls, directs, or modulates the movement or transfer of something (such as material, energy, or information) between two other entities.
-
C.
regulatesOutflowOf
Indicates that one entity controls, modulates, or governs the rate or amount of outflow from another entity.
-
D.
managesFlowTo
Indicates that one entity controls, regulates, or directs the movement or distribution of something (such as data, resources, or materials) to another entity.
-
E.
regulatesTrafficBetween
Indicates that one entity controls, manages, or directs the flow of traffic occurring between two other entities or locations.
- 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_69e2ff3071548190b62d1ac237397197 |
completed | April 18, 2026, 3:49 a.m. |
| NER | Named-entity recognition | batch_69f658a91ba0819084fbe3dd8a09f7cd |
completed | May 2, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69f6575ba12081909396036f78757a76 |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f657f2c8b08190bfeb3173ef78207d |
completed | May 2, 2026, 8 p.m. |
Created at: April 18, 2026, 6:25 a.m.