Triple
T37343927
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tora Liman Prison |
E927117
|
entity |
| Predicate | accessToLawyers |
P88347
|
FINISHED |
| Object | severely restricted |
—
|
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: severely restricted | Statement: [Tora Liman Prison, accessToLawyers, severely restricted]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessToLawyers Context triple: [Tora Liman Prison, accessToLawyers, severely restricted]
-
A.
numberOfLawyers
Indicates the quantity of lawyers associated with a given entity or situation.
-
B.
attorneysAre
Indicates that one or more entities serve in the role or capacity of attorneys for another entity or within a specified context.
-
C.
allowsRepresentationByLawyers
chosen
Indicates that one party permits or recognizes the right of another party to be represented by lawyers in a given context or proceeding.
-
D.
legalRepresentation
Indicates that one entity formally acts on behalf of another in legal matters, such as providing counsel, advocacy, or defense within a legal system.
-
E.
legalForum
Indicates the official legal venue or jurisdiction in which a dispute, case, or legal matter is to be heard or resolved.
- 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_69f76eb4e8a881908bd40da28f36fc7e |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb8c38a9688190be524246f5682107 |
completed | May 6, 2026, 6:45 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9c6e0481908565bd849e869b24 |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.