Triple
T4920952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | British Transport Police |
E110462
|
entity |
| Predicate | usesTextService |
P60044
|
FINISHED |
| Object | 61016 |
—
|
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: 61016 | Statement: [British Transport Police, usesTextService, 61016]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesTextService Context triple: [British Transport Police, usesTextService, 61016]
-
A.
allowsText
Indicates that one entity permits or supports the use, input, or display of textual content in relation to another entity.
-
B.
canDictateText
Indicates that one entity has the ability to produce or control text content, typically by speaking or issuing commands that are converted into written form.
-
C.
usesLetteredServices
Indicates that an entity makes use of services that are identified or categorized by letter-based designations.
-
D.
usedSupport
Indicates that one entity employed or relied on another entity as a means of support or assistance in performing an action or achieving a result.
-
E.
hasSupportService
Indicates that one entity provides or is associated with a support-related service for another entity.
- 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_69bd4413f9908190afcff44d7929cc4c |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6ffabccc81909115ece1b04e2061 |
completed | March 20, 2026, 4:04 p.m. |
| PD | Predicate disambiguation | batch_69bd6c3421588190ab08e92b9558042e |
completed | March 20, 2026, 3:48 p.m. |
| PDg | Predicate description generation | batch_69bd6e482984819087124216738f1e29 |
completed | March 20, 2026, 3:56 p.m. |
Created at: March 20, 2026, 1:30 p.m.