Triple
T34795353
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | R v Penguin Books Ltd |
E1003061
|
entity |
| Predicate | defenceCounsel |
P60566
|
FINISHED |
| Object | Gerald Gardiner |
—
|
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: Gerald Gardiner | Statement: [R v Penguin Books Ltd, defenceCounsel, Gerald Gardiner]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defenceCounsel Context triple: [R v Penguin Books Ltd, defenceCounsel, Gerald Gardiner]
-
A.
defenseLawyer
chosen
Indicates that one entity serves as the legal representative defending another entity in a legal proceeding or case.
-
B.
defendant
Indicates that an entity is the party accused or sued in a legal action or proceeding.
-
C.
hasDefenseCounsel
Indicates that a person or party is represented or assisted by a defense attorney or legal counsel in a legal matter.
-
D.
coDefendant
Indicates that two or more parties are jointly named and involved as defendants in the same legal case or proceeding.
-
E.
counselForProsecution
Indicates that an entity serves as a legal representative or advisor acting on behalf of the prosecution in a legal proceeding.
- 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_69f76db543808190b188c6c86a91491b |
completed | May 3, 2026, 3:45 p.m. |
| NER | Named-entity recognition | batch_69f78c61ed4c8190ad84c918fa9af55a |
completed | May 3, 2026, 5:56 p.m. |
| PD | Predicate disambiguation | batch_69f78b8cb3a881909ebaac1b503988c2 |
completed | May 3, 2026, 5:53 p.m. |
Created at: May 3, 2026, 3:59 p.m.