Triple
T30598712
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thames Magistrates' Court |
E778851
|
entity |
| Predicate | proceduralLink |
P170248
|
FINISHED |
| Object | HM Prison Belmarsh |
—
|
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: HM Prison Belmarsh | Statement: [Thames Magistrates' Court, proceduralLink, HM Prison Belmarsh]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: proceduralLink Context triple: [Thames Magistrates' Court, proceduralLink, HM Prison Belmarsh]
-
A.
providesProcedure
Indicates that one entity supplies, makes available, or performs a specific procedure for another entity.
-
B.
formsPrimaryLinkBetween
Indicates that one entity serves as the main or most important connection or linkage between two other entities.
-
C.
linkedProgram
Indicates that one program is associated or connected to another program in a meaningful or dependent way.
-
D.
proceduralStyle
Indicates that one entity employs or is characterized by a particular procedural style associated with another entity.
-
E.
proceduralRequirement
Indicates that one entity specifies or imposes a required procedure or process that must be followed by 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_69f224a1570c8190a85d3ac330479a79 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f68b121eac81909e90416207bc1157 |
completed | May 2, 2026, 11:38 p.m. |
| PD | Predicate disambiguation | batch_69f6860def1c81909d79e1f088c4b5e5 |
completed | May 2, 2026, 11:17 p.m. |
| PDg | Predicate description generation | batch_69f68a160374819084d720985f800dfc |
completed | May 2, 2026, 11:34 p.m. |
Created at: April 29, 2026, 8:25 p.m.